SlideShare una empresa de Scribd logo
1 de 28
Descargar para leer sin conexión
Rule Generalization Strategies
in Incremental Learning
of Disjunctive Concepts
Stefano Ferilli, Andrea Pazienza, Floriana Esposito
stefano.ferilli@uniba.it
Dipartimento di Informatica
Centro Interdipartimentale per la Logica e sue Applicazioni
Università di Bari
9th International Web Rule Symposium (RuleML)
August 2-5, 2015 – Berlin, Germany
Overview
● Introduction & Motivation
● Generalization Algorithm
● Selection Strategies
● Evaluation
● Conclusions & Future Work
Introduction
● Symbolic knowledge representations
● Mandatory for applications that
– Reproduce the human inferential behavior
– May be required to explain their decisions in human-
understandable terms
● 2 kinds of concept definitions
– Conjunctive: a single definition accounts for all instances
of the concept
– Disjunctive: several alternate conjunctive definitions
(components)
● Each covers part of the full concept extension
● Psychological studies have established that capturing and
dealing with the latter is much harder for humans
● Pervasive and fundamental in most real-world domains
Introduction
● Knowledge acquisition bottleneck
● (Symbolic) Machine Learning (ML) systems
– Supervised setting: concept definitions inferred from
descriptions of valid (positive) or invalid (negative)
instances (examples)
● Batch: whole set of examples available (classical setting in ML)
– Components learned by progressive coverage strategies
– Definitions are immutable
● If additional examples are provided, learning must start
from scratch considering the extended set of examples
● Incremental: new examples may be provided after a tentative
definition is already available
– Components emerge as long as they are found
– Definitions may be changed/refined if wrong
Motivations
● Incremental approach
– If the available concept definition cannot properly account
for a new example, it must be refined (revised, changed,
modified) so that the new version properly accounts for
both the old and the new examples
– Progressive covering strategy not applicable
● Issue of disjunctive definitions becomes particularly relevant
– When many components can be refined, there is no unique
way for determining which one is most profitably refined
– Refining different components results in different updated
definitions, that become implicit constraints on how the
definition itself may evolve when additional examples will
become available in the future
● The learned model depends
– on the order in which the examples are provided
– on the choice of the component to be refined at each step
Motivations
● Abstract Diagnosis: Identification of the part of the
theory that misclassifies the example
– Tricky in the case of disjunctive concepts
● Several alternate conjunctive definitions are available
– If a positive example is not covered, no component of the
current definition accounts for it (omission error)
● All candidate to generalization
– Generalizing all components, each component would
account alone for all positive examples
● Contradiction: the concept is conjunctive
● Over-generalization: the theory would be more prone to
covering forthcoming negative examples
– Problem not present in batch learning
Motivations
● Problem
– A single component of a disjunctive concept is to be
generalized
● Guided solutions may improve effectiveness and efficiency of the
overall outcome compared to a random strategy
● Objective
– Propose and evaluate different strategies for determining
the order in which the components should be considered
for generalization
● If the generalization of a component fails, generalization of the
next component in the ordering is attempted
Motivations
● Questions:
– what sensible strategies can be defined?
– what are their expected pros and cons?
– what is their effect on the quality of the theory?
– what about their consequences on the effectiveness and
efficiency of the learning process?
● Starting point
– InTheLEx (Incremental Theory Learner from Examples)
● fully incremental
● can learn disjunctive concept definitions
● refinement strategy can be tuned to suitably adapt its behavior
InTheLEx
● Learns hierarchical theories from positive and
negative examples
● Fully incremental
– May start from an empty theory and from the first
available example
● Necessary in most real-world application domains
●
DatalogOI
– Concept definitions and examples expressed as rules
● Example: example :- observation
● Rule: concept :- conjunctive definition
– Disjunctive concepts: several rules for the same concept
InTheLEx: Representation
– Theory that defines a disjunctive concept (4 components)
● ball(A) :- weight_medium(A), air_filled(A), has_patches(A),
horizontal_diameter(A,B), vertical_diameter(A,C), equal(B,C). %generic
● ball(A) :- weight_medium(A), air_filled(A), has_patches(A,B),
horizontal_diameter(A,B), vertical_diameter(A,C), larger(B,C). %rugby
● ball(A) :- weight_heavy(A), has_holes(A), horizontal_diameter(A,B),
vertical_diameter(A,C), equal(B,C). %bowling
● ball(A) :- weight_light(A), regular_shape(A), horizontal_diameter(A,B),
vertical_diameter(A,C), equal(B,C). %small
– Examples:
● ball(e) :- weight_medium(e), has_patches(e), air_filled(e),
made_of_leather(e), horizontal_diameter(e,he), vertical_diameter(e,ve),
equal(he,ve). %soccer Etrusco FIFA World Cup 1990
● neg(ball(s1)) :- weight_light(s1), made_of_snow(s1),
irregular_shape(s1), horizontal_diameter(s1,hs1),
vertical_diameter(s1,vs1), smaller(hs1,vs1). %snowball
● neg(ball(s2)) :- weight_light(s2), made_of_paper(s2),
horizontal_diameter(s2,hs2), vertical_diameter(s2,vs2), larger(hs2,vs2).
%spitball
InTheLEx: Theory Revision
● Logic theory revision process
– Given a new example
● No effect on the theory if
– negative and not covered
● not predicted by the theory to belong to the concept
– positive and covered
● predicted by the theory to belong to the concept
● In all the other cases, the theory needs to be revised
– Positive example not covered  generalization of the theory
– Negative example covered  specialization of the theory
– Refinements (generalizations or specializations) must
preserve correctness with respect to the entire set of
currently available examples
● If no candidate refinement fulfills this requirement, the specific
problematic example is stored as an exception
InTheLEx: Generalization
– Procedure Generalize
(E: positive example, T: theory, M: negative examples);
● L := list of the rules in the definition of E's concept
while not generalized and L   do
– Select from L a rule C for generalization
– L' := generalize(C,E) (* list of generalizations *)
– while not generalized and L'   do
● Select next best generalization C' from L'
●
if (T  {C}  {C'} is consistent wrt M then
● Implement C' in T
– Remove C from L
● if not generalized then
– C' := E with constants turned into variables
– if (T  {C}  {C'} is consistent wrt M then
● Implement C' in T
– else
● Implement E in T as an exception
InTheLEx: Generalization
– Comments
● Due to theoretical and implementation details, the generalization
operator used might return several incomparable generalizations
● Implementation of the theoretical generalization operator would
be computationally infeasible, even for relatively small rules
– Similarity-based approximation
● Experiments have shown that it comes very close, and
often catches, least general generalizations
● First example of a new concept
– First rule rule added for that concept
● Initial tentative conjunctive definition of the concept
● Conjunctive definition turns out to be insufficient
– Second rule added for that concept
● The concept becomes disjunctive
● Subsequent addition of rules for that concept
– Extend the ‘disjunctiveness’ of the concept
Clause Selection Strategy
● 5 strategies for determining the order in which the
components of a disjunctive concept definition are
to be considered for generalization
– Each component in the ordering considered only after
generalization attempts have failed on all previous
components
● Initial components have more chances to be generalized
– No direct connection between age and length of a rule
● Older rules might have had more chances of refinement
● Whether this means that they are also shorter (i.e., more
general) mainly depends on
– Ranking strategy
– Specific examples that are encountered and on their order
● Not controllable in a real-world setting
Clause Selection Strategy
● O: Older elements first
– Same order as they were added to the theory
● The most straightforward. A sort of baseline
● Static: position of each component in the processing order fixed
when component is added
– Generalizations are monotonic (progressively remove
constraints)
● Strategy expected to yield very refined (short, more
human-readable and understandable) initial components
and very raw (long) final ones
– After several refinements, it is likely that initial components
have reached a nearly final and quite stable form
● All attempts to further refine them are likely to fail
● The computational time spent in these attempts, albeit
presumably not huge, will be wasted
● Runtime expected to grow as long as the life of the
theory proceeds
Clause Selection Strategy
● N: Newer elements first
– Reverse order as they were added to the theory
● Also quite straightforward
● Static, but not obvious to foresee what will be the shape and
evolution of the components
– Immediately after the addition of a new component, it will
undergo a generalization attempt at the first non-covered
positive example
● ‘average’ level of generality in the definition expected to
be less than in the previous option
● There should be no completely raw components in
the definition
● Many chances that such an attempt is successful for any
example, but the resulting generalization might leverage
features that might be not very related to the correct
concept definition
Clause Selection Strategy
● L: Longer elements first
– Decreasing number of conjuncts
● Specifically considers the level of refinement
– Low variance in degree of refinement among components
expected
● Can be considered as an evolution of N
– Not just the most recently added component is favored for
generalization
● The more conjuncts in a component, the more specialized the
component
– More room for generalization
● Avoid waste of time trying to generalize very refined rules
that would hardly yield consistent generalizations
● On the other hand, generalizing a longer rule is expected
to take more time than generalizing shorter ones
Clause Selection Strategy
● S: Shorter elements first
– Increasing number of conjuncts
● Specifically considers the level of refinement
– Opposite behavior than L
● May confirm the possible advantage of spending time in
trying harder but more promising generalizations versus
spending time in trying easier but less promising ones
first
● Can be considered as an evolution of O
– Tries to generalize first more refined components
● Largest variance in degree of refinement (number of
conjuncts in rule premises) among components expected
Clause Selection Strategy
● ~: More similar elements first
– Decreasing similarity with the uncovered example
● Only content-based strategy
– Same similarity as in InTheLEx’s generalization operator
●
Disjunctive components  different actualizations of a concept
– Small intersection expected between the sets of examples
covered by different components
● Similarity assessment may allow to identify the appropriate
component to be generalized for a given example
– Odd generalizations for mismatched component-example
● Coverage and generalization problems
● Bad theory, inefficient refinements
– One might expect that over-generalization is avoided
– Generalization more easily computed, but overhead to
compute the similarity
● Does the improvement compensate the overhead?
Evaluation
● Real-world dataset: Scientific papers
– 353 layout descriptions of first pages
– 4 classes: Elsevier journals, SVLN, JMLR, MLJ
● Classification: learn definitions for these classes
● Understanding: the significant components in the papers
– Title, Author, Abstract, Keywords
● First-Order Logic representation needed to express spatial
relationships among the page components
● Complex dataset
– Some layout styles are quite similar
– 67920 atoms in observations
● avg per observation >192 atoms, some >400 atoms
– Much indeterminacy
● Membership relation of layout components to pages
Evaluation: Parameters
● Qualitative
– # comp in the disjunctive concept definition
● Less components yield a more compact theory, which does not
necessarily provide for greater accuracy
– avg length of components
● More conjuncts, more specific -and less refined- concept
– # exc negative exceptions
● More exceptions, worse theory
● Quantitative
– acc (accuracy)
● Prediction capabilities of the theory on test examples
– time needed to carry out the learning task
● Efficiency (computational cost) for the different ranking strategies
Evaluation
● Incremental approach justified
– New instances of documents continuously available in
time
● Comparison of all strategies
– Random not tried
● O or N are somehow random
– Just append definitions as long as they are generated,
without any insight
● 10-fold cross-validation procedure
– Classification task used to check in detail the behavior of
the different strategies
– Understanding task used to assess the statistical
significance of the difference in performance between
different strategies
Evaluation: Classification
● Useful results only for MLJ and SVLN
– Elsevier and JMLR: always single-rule definitions
● Ranking approach not applicable
– Examples for Elsevier and JMLR still played a role as
negative examples for the other classes
– Some expectations confirmed
● Runtime: N always best (often the first generalization attempt
succeeds); ~ worst (need for computing the similarity of each
component and the example)
● Number of exceptions: ~ always best (improved selection of
components for generalization); S also good
● Aggregated indicator: N always wins
– Sum of ranking positions for the different parameters (the
smaller, the better)
Evaluation: Classification
Evaluation: Classification
– Rest of behavior somehow mixed
● SVLN: much less variance than in MLJ
– Definition quite clear and examples quite significant?
● MLJ: Impact of the ranking strategies much clearer
– Substantial agreement between quality-related indicators: for
each approach, either all tend to be good (as in ~) or all tend
to be bad (as in S and O)
● Interesting indications from single folds
– 3: peak in runtime and number of exceptions for S and O
● runtime a consequence of the unsuccessful search for
specializations, that in turn may have some connection
with the quality of the theory
● S is a kind of evolution of O
– 8: accuracy increases from 82% to 94% for ~ and L
● Content-based approach improves quality of the theory in
difficult situations
Evaluation: Understanding
● Strategy on the
row equal (=),
better (+) or
worse (–) than
the one on the
column
● Best strategy
in bold
Evaluation: Understanding
● Quite different, albeit run on the same data
– When the difference is significant, in general analogous
behavior of L and ~ for accuracy (which is greater),
number of components and number of negative
exceptions. As expected, longer runtime for ~
– Also O and S have in general an analogous behavior, but
do not reach as good results as L and ~
– N not outstanding for performance, but better than O (the
baseline) for all parameters except runtime
– On the classification task, average length of components
using L significantly larger than all the others
● Returns more balanced components
but more accuracy and less negative exceptions
Conclusions & Future Work
● Disjunctive concept definitions tricky
– Each component covers a subset of positive examples,
ensuring consistency with all negative examples
● In incremental learning, when a new positive example is not
recognized by the current theory, one component must be
generalized
– Omission error (no specific component responsible)
● The system must decide the order in which the elements
are to be considered for trying a generalization
– 5 strategies proposed
● The outcomes confirm some of the expectations for the various
strategies, but we need
– More extensive experimentation to have confirmations and
additional details
– Identification of further strategies and refinement of the
proposed ones

Más contenido relacionado

La actualidad más candente

artificial intelligence
artificial intelligenceartificial intelligence
artificial intelligenceR A Akerkar
 
Lec 3 knowledge acquisition representation and inference
Lec 3  knowledge acquisition representation and inferenceLec 3  knowledge acquisition representation and inference
Lec 3 knowledge acquisition representation and inferenceEyob Sisay
 
Mca4040 analysis and design of algorithm
Mca4040  analysis and design of algorithmMca4040  analysis and design of algorithm
Mca4040 analysis and design of algorithmsmumbahelp
 
Artificial intelligence and first order logic
Artificial intelligence and first order logicArtificial intelligence and first order logic
Artificial intelligence and first order logicparsa rafiq
 
Extraction Based automatic summarization
Extraction Based automatic summarizationExtraction Based automatic summarization
Extraction Based automatic summarizationAbdelaziz Al-Rihawi
 
Document Summarization
Document SummarizationDocument Summarization
Document SummarizationPratik Kumar
 
Practical Non-Monotonic Reasoning
Practical Non-Monotonic ReasoningPractical Non-Monotonic Reasoning
Practical Non-Monotonic ReasoningGuido Governatori
 
2010 PACLIC - pay attention to categories
2010 PACLIC - pay attention to categories2010 PACLIC - pay attention to categories
2010 PACLIC - pay attention to categoriesWarNik Chow
 
Discrete Mathematics
Discrete MathematicsDiscrete Mathematics
Discrete Mathematicsmetamath
 
NLP Project Presentation
NLP Project PresentationNLP Project Presentation
NLP Project PresentationAryak Sengupta
 
Types of parsers
Types of parsersTypes of parsers
Types of parsersSabiha M
 
Latent Topic-semantic Indexing based Automatic Text Summarization
Latent Topic-semantic Indexing based Automatic Text SummarizationLatent Topic-semantic Indexing based Automatic Text Summarization
Latent Topic-semantic Indexing based Automatic Text SummarizationElaheh Barati
 

La actualidad más candente (20)

Structured Knowledge Representation
Structured Knowledge RepresentationStructured Knowledge Representation
Structured Knowledge Representation
 
artificial intelligence
artificial intelligenceartificial intelligence
artificial intelligence
 
Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
 
AI: Logic in AI
AI: Logic in AIAI: Logic in AI
AI: Logic in AI
 
Lec 3 knowledge acquisition representation and inference
Lec 3  knowledge acquisition representation and inferenceLec 3  knowledge acquisition representation and inference
Lec 3 knowledge acquisition representation and inference
 
Mca4040 analysis and design of algorithm
Mca4040  analysis and design of algorithmMca4040  analysis and design of algorithm
Mca4040 analysis and design of algorithm
 
Artificial intelligence and first order logic
Artificial intelligence and first order logicArtificial intelligence and first order logic
Artificial intelligence and first order logic
 
Text summarization
Text summarization Text summarization
Text summarization
 
Extraction Based automatic summarization
Extraction Based automatic summarizationExtraction Based automatic summarization
Extraction Based automatic summarization
 
Document Summarization
Document SummarizationDocument Summarization
Document Summarization
 
Practical Non-Monotonic Reasoning
Practical Non-Monotonic ReasoningPractical Non-Monotonic Reasoning
Practical Non-Monotonic Reasoning
 
Prolog
PrologProlog
Prolog
 
Text Summarization
Text SummarizationText Summarization
Text Summarization
 
1909 paclic
1909 paclic1909 paclic
1909 paclic
 
2010 PACLIC - pay attention to categories
2010 PACLIC - pay attention to categories2010 PACLIC - pay attention to categories
2010 PACLIC - pay attention to categories
 
Discrete Mathematics
Discrete MathematicsDiscrete Mathematics
Discrete Mathematics
 
Parser
ParserParser
Parser
 
NLP Project Presentation
NLP Project PresentationNLP Project Presentation
NLP Project Presentation
 
Types of parsers
Types of parsersTypes of parsers
Types of parsers
 
Latent Topic-semantic Indexing based Automatic Text Summarization
Latent Topic-semantic Indexing based Automatic Text SummarizationLatent Topic-semantic Indexing based Automatic Text Summarization
Latent Topic-semantic Indexing based Automatic Text Summarization
 

Destacado

Basic Competitive Advantages
Basic Competitive AdvantagesBasic Competitive Advantages
Basic Competitive AdvantagesKohJung An
 
Strategic Alliance
Strategic AllianceStrategic Alliance
Strategic AllianceWalid Saafan
 
Innovation & Project Management - Partners in Growth
Innovation & Project Management - Partners in GrowthInnovation & Project Management - Partners in Growth
Innovation & Project Management - Partners in GrowthThink For A Change
 
6 Steps to Creating a Content Marketing Strategy - #SMMW15
6 Steps to Creating a Content Marketing Strategy - #SMMW156 Steps to Creating a Content Marketing Strategy - #SMMW15
6 Steps to Creating a Content Marketing Strategy - #SMMW15Joe Pulizzi
 
Liquidation strategy retrenchment strategies - corporate level strategies -...
Liquidation strategy   retrenchment strategies - corporate level strategies -...Liquidation strategy   retrenchment strategies - corporate level strategies -...
Liquidation strategy retrenchment strategies - corporate level strategies -...manumelwin
 
Business harvesting
Business harvestingBusiness harvesting
Business harvestingdeepak gupta
 
Growth strategy
Growth strategyGrowth strategy
Growth strategySumit Rai
 
Globalization strategy - Walmart
Globalization strategy - WalmartGlobalization strategy - Walmart
Globalization strategy - WalmartPradeep Loganathan
 
Porter's Generic Strategies with examples
Porter's Generic Strategies with examplesPorter's Generic Strategies with examples
Porter's Generic Strategies with examplesdipalij07
 

Destacado (10)

Basic Competitive Advantages
Basic Competitive AdvantagesBasic Competitive Advantages
Basic Competitive Advantages
 
Strategic Alliance
Strategic AllianceStrategic Alliance
Strategic Alliance
 
Innovation & Project Management - Partners in Growth
Innovation & Project Management - Partners in GrowthInnovation & Project Management - Partners in Growth
Innovation & Project Management - Partners in Growth
 
6 Steps to Creating a Content Marketing Strategy - #SMMW15
6 Steps to Creating a Content Marketing Strategy - #SMMW156 Steps to Creating a Content Marketing Strategy - #SMMW15
6 Steps to Creating a Content Marketing Strategy - #SMMW15
 
Liquidation strategy retrenchment strategies - corporate level strategies -...
Liquidation strategy   retrenchment strategies - corporate level strategies -...Liquidation strategy   retrenchment strategies - corporate level strategies -...
Liquidation strategy retrenchment strategies - corporate level strategies -...
 
Business harvesting
Business harvestingBusiness harvesting
Business harvesting
 
Growth strategy
Growth strategyGrowth strategy
Growth strategy
 
Chapter 3 grand strategy
Chapter 3 grand strategyChapter 3 grand strategy
Chapter 3 grand strategy
 
Globalization strategy - Walmart
Globalization strategy - WalmartGlobalization strategy - Walmart
Globalization strategy - Walmart
 
Porter's Generic Strategies with examples
Porter's Generic Strategies with examplesPorter's Generic Strategies with examples
Porter's Generic Strategies with examples
 

Similar a RuleML2015: Rule Generalization Strategies in Incremental Learning of Disjunctive Concepts

Learning sets of Rules by Dr.C.R.Dhivyaa Kongu Engineering College
Learning sets of Rules by Dr.C.R.Dhivyaa Kongu Engineering CollegeLearning sets of Rules by Dr.C.R.Dhivyaa Kongu Engineering College
Learning sets of Rules by Dr.C.R.Dhivyaa Kongu Engineering CollegeDhivyaa C.R
 
ANALYTIC METHOD IMPLEMENTATION WITH A TRIGONOMETRY PROBLEM SOLVER
ANALYTIC METHOD IMPLEMENTATION WITH A TRIGONOMETRY PROBLEM SOLVERANALYTIC METHOD IMPLEMENTATION WITH A TRIGONOMETRY PROBLEM SOLVER
ANALYTIC METHOD IMPLEMENTATION WITH A TRIGONOMETRY PROBLEM SOLVERCourtney Esco
 
Fundamentals of Quantitative Analysis
Fundamentals of Quantitative AnalysisFundamentals of Quantitative Analysis
Fundamentals of Quantitative AnalysisJubayer Alam Shoikat
 
Blueprinting and drafting questions Liz Norman ANZCVS 2015
Blueprinting and drafting questions Liz Norman ANZCVS 2015Blueprinting and drafting questions Liz Norman ANZCVS 2015
Blueprinting and drafting questions Liz Norman ANZCVS 2015Liz Norman
 
Report
ReportReport
Reportbutest
 
Machine learning - session 3
Machine learning - session 3Machine learning - session 3
Machine learning - session 3Luis Borbon
 
What is modeling.pptx
What is modeling.pptxWhat is modeling.pptx
What is modeling.pptxBerhe Tekle
 
internship project1 report
internship project1 reportinternship project1 report
internship project1 reportsheyk98
 
L3 hypothesis or research question
L3 hypothesis or research questionL3 hypothesis or research question
L3 hypothesis or research questionSeppo Karrila
 
Statistical Learning and Model Selection module 2.pptx
Statistical Learning and Model Selection module 2.pptxStatistical Learning and Model Selection module 2.pptx
Statistical Learning and Model Selection module 2.pptxnagarajan740445
 
Goal Decomposition and Abductive Reasoning for Policy Analysis and Refinement
Goal Decomposition and Abductive Reasoning for Policy Analysis and RefinementGoal Decomposition and Abductive Reasoning for Policy Analysis and Refinement
Goal Decomposition and Abductive Reasoning for Policy Analysis and RefinementEmil Lupu
 
A Review of Constraint Programming
A Review of Constraint ProgrammingA Review of Constraint Programming
A Review of Constraint ProgrammingEditor IJCATR
 
AI_Unit-4_Learning.pptx
AI_Unit-4_Learning.pptxAI_Unit-4_Learning.pptx
AI_Unit-4_Learning.pptxMohammadAsim91
 
Chapter 24 theory testing and theory evaluation
Chapter 24 theory testing and theory evaluationChapter 24 theory testing and theory evaluation
Chapter 24 theory testing and theory evaluationstanbridge
 
A brief introduction to Searn Algorithm
A brief introduction to Searn AlgorithmA brief introduction to Searn Algorithm
A brief introduction to Searn AlgorithmSupun Abeysinghe
 
Grading criteria and marking schemes liz norman anzcvs 2015
Grading criteria and marking schemes liz norman anzcvs 2015Grading criteria and marking schemes liz norman anzcvs 2015
Grading criteria and marking schemes liz norman anzcvs 2015Liz Norman
 
Operation research history and overview application limitation
Operation research history and overview application limitationOperation research history and overview application limitation
Operation research history and overview application limitationBalaji P
 
Inductive & Deductive Method/Dr.Jaganmohana Rao Gurugubelli
Inductive & Deductive Method/Dr.Jaganmohana Rao GurugubelliInductive & Deductive Method/Dr.Jaganmohana Rao Gurugubelli
Inductive & Deductive Method/Dr.Jaganmohana Rao GurugubelliDr.Jaganmohana Rao Gurugubelli
 

Similar a RuleML2015: Rule Generalization Strategies in Incremental Learning of Disjunctive Concepts (20)

Learning sets of Rules by Dr.C.R.Dhivyaa Kongu Engineering College
Learning sets of Rules by Dr.C.R.Dhivyaa Kongu Engineering CollegeLearning sets of Rules by Dr.C.R.Dhivyaa Kongu Engineering College
Learning sets of Rules by Dr.C.R.Dhivyaa Kongu Engineering College
 
UNIT V (5).pptx
UNIT V (5).pptxUNIT V (5).pptx
UNIT V (5).pptx
 
ANALYTIC METHOD IMPLEMENTATION WITH A TRIGONOMETRY PROBLEM SOLVER
ANALYTIC METHOD IMPLEMENTATION WITH A TRIGONOMETRY PROBLEM SOLVERANALYTIC METHOD IMPLEMENTATION WITH A TRIGONOMETRY PROBLEM SOLVER
ANALYTIC METHOD IMPLEMENTATION WITH A TRIGONOMETRY PROBLEM SOLVER
 
Fundamentals of Quantitative Analysis
Fundamentals of Quantitative AnalysisFundamentals of Quantitative Analysis
Fundamentals of Quantitative Analysis
 
Blueprinting and drafting questions Liz Norman ANZCVS 2015
Blueprinting and drafting questions Liz Norman ANZCVS 2015Blueprinting and drafting questions Liz Norman ANZCVS 2015
Blueprinting and drafting questions Liz Norman ANZCVS 2015
 
Report
ReportReport
Report
 
Machine learning - session 3
Machine learning - session 3Machine learning - session 3
Machine learning - session 3
 
What is modeling.pptx
What is modeling.pptxWhat is modeling.pptx
What is modeling.pptx
 
internship project1 report
internship project1 reportinternship project1 report
internship project1 report
 
L3 hypothesis or research question
L3 hypothesis or research questionL3 hypothesis or research question
L3 hypothesis or research question
 
Statistical Learning and Model Selection module 2.pptx
Statistical Learning and Model Selection module 2.pptxStatistical Learning and Model Selection module 2.pptx
Statistical Learning and Model Selection module 2.pptx
 
Goal Decomposition and Abductive Reasoning for Policy Analysis and Refinement
Goal Decomposition and Abductive Reasoning for Policy Analysis and RefinementGoal Decomposition and Abductive Reasoning for Policy Analysis and Refinement
Goal Decomposition and Abductive Reasoning for Policy Analysis and Refinement
 
A Review of Constraint Programming
A Review of Constraint ProgrammingA Review of Constraint Programming
A Review of Constraint Programming
 
AI_Unit-4_Learning.pptx
AI_Unit-4_Learning.pptxAI_Unit-4_Learning.pptx
AI_Unit-4_Learning.pptx
 
Chapter 24 theory testing and theory evaluation
Chapter 24 theory testing and theory evaluationChapter 24 theory testing and theory evaluation
Chapter 24 theory testing and theory evaluation
 
A brief introduction to Searn Algorithm
A brief introduction to Searn AlgorithmA brief introduction to Searn Algorithm
A brief introduction to Searn Algorithm
 
Grading criteria and marking schemes liz norman anzcvs 2015
Grading criteria and marking schemes liz norman anzcvs 2015Grading criteria and marking schemes liz norman anzcvs 2015
Grading criteria and marking schemes liz norman anzcvs 2015
 
Policy gradient
Policy gradientPolicy gradient
Policy gradient
 
Operation research history and overview application limitation
Operation research history and overview application limitationOperation research history and overview application limitation
Operation research history and overview application limitation
 
Inductive & Deductive Method/Dr.Jaganmohana Rao Gurugubelli
Inductive & Deductive Method/Dr.Jaganmohana Rao GurugubelliInductive & Deductive Method/Dr.Jaganmohana Rao Gurugubelli
Inductive & Deductive Method/Dr.Jaganmohana Rao Gurugubelli
 

Más de RuleML

Aggregates in Recursion: Issues and Solutions
Aggregates in Recursion: Issues and SolutionsAggregates in Recursion: Issues and Solutions
Aggregates in Recursion: Issues and SolutionsRuleML
 
A software agent controlling 2 robot arms in co-operating concurrent tasks
A software agent controlling 2 robot arms in co-operating concurrent tasksA software agent controlling 2 robot arms in co-operating concurrent tasks
A software agent controlling 2 robot arms in co-operating concurrent tasksRuleML
 
Port Clearance Rules in PSOA RuleML: From Controlled-English Regulation to Ob...
Port Clearance Rules in PSOA RuleML: From Controlled-English Regulation to Ob...Port Clearance Rules in PSOA RuleML: From Controlled-English Regulation to Ob...
Port Clearance Rules in PSOA RuleML: From Controlled-English Regulation to Ob...RuleML
 
RuleML 2015: When Processes Rule Events
RuleML 2015: When Processes Rule EventsRuleML 2015: When Processes Rule Events
RuleML 2015: When Processes Rule EventsRuleML
 
RuleML 2015: Ontology Reasoning using Rules in an eHealth Context
RuleML 2015: Ontology Reasoning using Rules in an eHealth ContextRuleML 2015: Ontology Reasoning using Rules in an eHealth Context
RuleML 2015: Ontology Reasoning using Rules in an eHealth ContextRuleML
 
RuleML 2015: Semantics of Notation3 Logic: A Solution for Implicit Quantifica...
RuleML 2015: Semantics of Notation3 Logic: A Solution for Implicit Quantifica...RuleML 2015: Semantics of Notation3 Logic: A Solution for Implicit Quantifica...
RuleML 2015: Semantics of Notation3 Logic: A Solution for Implicit Quantifica...RuleML
 
Challenge@RuleML2015 Developing Situation-Aware Applications for Disaster Man...
Challenge@RuleML2015 Developing Situation-Aware Applications for Disaster Man...Challenge@RuleML2015 Developing Situation-Aware Applications for Disaster Man...
Challenge@RuleML2015 Developing Situation-Aware Applications for Disaster Man...RuleML
 
Rule Generalization Strategies in Incremental Learning of Disjunctive Concepts
Rule Generalization Strategies in Incremental Learning of Disjunctive ConceptsRule Generalization Strategies in Incremental Learning of Disjunctive Concepts
Rule Generalization Strategies in Incremental Learning of Disjunctive ConceptsRuleML
 
RuleML 2015 Constraint Handling Rules - What Else?
RuleML 2015 Constraint Handling Rules - What Else?RuleML 2015 Constraint Handling Rules - What Else?
RuleML 2015 Constraint Handling Rules - What Else?RuleML
 
RuleML2015 The Herbrand Manifesto - Thinking Inside the Box
RuleML2015 The Herbrand Manifesto - Thinking Inside the Box RuleML2015 The Herbrand Manifesto - Thinking Inside the Box
RuleML2015 The Herbrand Manifesto - Thinking Inside the Box RuleML
 
Industry@RuleML2015: Norwegian State of Estate A Reporting Service for the St...
Industry@RuleML2015: Norwegian State of Estate A Reporting Service for the St...Industry@RuleML2015: Norwegian State of Estate A Reporting Service for the St...
Industry@RuleML2015: Norwegian State of Estate A Reporting Service for the St...RuleML
 
A Service for Improving the Assignments of Common Agriculture Policy Funds to...
A Service for Improving the Assignments of Common Agriculture Policy Funds to...A Service for Improving the Assignments of Common Agriculture Policy Funds to...
A Service for Improving the Assignments of Common Agriculture Policy Funds to...RuleML
 
RuleML2015: Binary Frontier-guarded ASP with Function Symbols
RuleML2015: Binary Frontier-guarded ASP with Function SymbolsRuleML2015: Binary Frontier-guarded ASP with Function Symbols
RuleML2015: Binary Frontier-guarded ASP with Function SymbolsRuleML
 
RuleML2015: API4KP Metamodel: A Meta-API for Heterogeneous Knowledge Platforms
RuleML2015: API4KP Metamodel: A Meta-API for Heterogeneous Knowledge PlatformsRuleML2015: API4KP Metamodel: A Meta-API for Heterogeneous Knowledge Platforms
RuleML2015: API4KP Metamodel: A Meta-API for Heterogeneous Knowledge PlatformsRuleML
 
RuleML2015: Rule-Based Exploration of Structured Data in the Browser
RuleML2015: Rule-Based Exploration of Structured Data in the BrowserRuleML2015: Rule-Based Exploration of Structured Data in the Browser
RuleML2015: Rule-Based Exploration of Structured Data in the BrowserRuleML
 
RuleML2015: Ontology-Based Multidimensional Contexts with Applications to Qua...
RuleML2015: Ontology-Based Multidimensional Contexts with Applications to Qua...RuleML2015: Ontology-Based Multidimensional Contexts with Applications to Qua...
RuleML2015: Ontology-Based Multidimensional Contexts with Applications to Qua...RuleML
 
RuleML2015: Compact representation of conditional probability for rule-based...
RuleML2015:  Compact representation of conditional probability for rule-based...RuleML2015:  Compact representation of conditional probability for rule-based...
RuleML2015: Compact representation of conditional probability for rule-based...RuleML
 
RuleML2015: Learning Characteristic Rules in Geographic Information Systems
RuleML2015: Learning Characteristic Rules in Geographic Information SystemsRuleML2015: Learning Characteristic Rules in Geographic Information Systems
RuleML2015: Learning Characteristic Rules in Geographic Information SystemsRuleML
 
RuleML2015: Using Substitutive Itemset Mining Framework for Finding Synonymou...
RuleML2015: Using Substitutive Itemset Mining Framework for Finding Synonymou...RuleML2015: Using Substitutive Itemset Mining Framework for Finding Synonymou...
RuleML2015: Using Substitutive Itemset Mining Framework for Finding Synonymou...RuleML
 
RuleML2015: User Extensible System to Identify Problems in OWL Ontologies and...
RuleML2015: User Extensible System to Identify Problems in OWL Ontologies and...RuleML2015: User Extensible System to Identify Problems in OWL Ontologies and...
RuleML2015: User Extensible System to Identify Problems in OWL Ontologies and...RuleML
 

Más de RuleML (20)

Aggregates in Recursion: Issues and Solutions
Aggregates in Recursion: Issues and SolutionsAggregates in Recursion: Issues and Solutions
Aggregates in Recursion: Issues and Solutions
 
A software agent controlling 2 robot arms in co-operating concurrent tasks
A software agent controlling 2 robot arms in co-operating concurrent tasksA software agent controlling 2 robot arms in co-operating concurrent tasks
A software agent controlling 2 robot arms in co-operating concurrent tasks
 
Port Clearance Rules in PSOA RuleML: From Controlled-English Regulation to Ob...
Port Clearance Rules in PSOA RuleML: From Controlled-English Regulation to Ob...Port Clearance Rules in PSOA RuleML: From Controlled-English Regulation to Ob...
Port Clearance Rules in PSOA RuleML: From Controlled-English Regulation to Ob...
 
RuleML 2015: When Processes Rule Events
RuleML 2015: When Processes Rule EventsRuleML 2015: When Processes Rule Events
RuleML 2015: When Processes Rule Events
 
RuleML 2015: Ontology Reasoning using Rules in an eHealth Context
RuleML 2015: Ontology Reasoning using Rules in an eHealth ContextRuleML 2015: Ontology Reasoning using Rules in an eHealth Context
RuleML 2015: Ontology Reasoning using Rules in an eHealth Context
 
RuleML 2015: Semantics of Notation3 Logic: A Solution for Implicit Quantifica...
RuleML 2015: Semantics of Notation3 Logic: A Solution for Implicit Quantifica...RuleML 2015: Semantics of Notation3 Logic: A Solution for Implicit Quantifica...
RuleML 2015: Semantics of Notation3 Logic: A Solution for Implicit Quantifica...
 
Challenge@RuleML2015 Developing Situation-Aware Applications for Disaster Man...
Challenge@RuleML2015 Developing Situation-Aware Applications for Disaster Man...Challenge@RuleML2015 Developing Situation-Aware Applications for Disaster Man...
Challenge@RuleML2015 Developing Situation-Aware Applications for Disaster Man...
 
Rule Generalization Strategies in Incremental Learning of Disjunctive Concepts
Rule Generalization Strategies in Incremental Learning of Disjunctive ConceptsRule Generalization Strategies in Incremental Learning of Disjunctive Concepts
Rule Generalization Strategies in Incremental Learning of Disjunctive Concepts
 
RuleML 2015 Constraint Handling Rules - What Else?
RuleML 2015 Constraint Handling Rules - What Else?RuleML 2015 Constraint Handling Rules - What Else?
RuleML 2015 Constraint Handling Rules - What Else?
 
RuleML2015 The Herbrand Manifesto - Thinking Inside the Box
RuleML2015 The Herbrand Manifesto - Thinking Inside the Box RuleML2015 The Herbrand Manifesto - Thinking Inside the Box
RuleML2015 The Herbrand Manifesto - Thinking Inside the Box
 
Industry@RuleML2015: Norwegian State of Estate A Reporting Service for the St...
Industry@RuleML2015: Norwegian State of Estate A Reporting Service for the St...Industry@RuleML2015: Norwegian State of Estate A Reporting Service for the St...
Industry@RuleML2015: Norwegian State of Estate A Reporting Service for the St...
 
A Service for Improving the Assignments of Common Agriculture Policy Funds to...
A Service for Improving the Assignments of Common Agriculture Policy Funds to...A Service for Improving the Assignments of Common Agriculture Policy Funds to...
A Service for Improving the Assignments of Common Agriculture Policy Funds to...
 
RuleML2015: Binary Frontier-guarded ASP with Function Symbols
RuleML2015: Binary Frontier-guarded ASP with Function SymbolsRuleML2015: Binary Frontier-guarded ASP with Function Symbols
RuleML2015: Binary Frontier-guarded ASP with Function Symbols
 
RuleML2015: API4KP Metamodel: A Meta-API for Heterogeneous Knowledge Platforms
RuleML2015: API4KP Metamodel: A Meta-API for Heterogeneous Knowledge PlatformsRuleML2015: API4KP Metamodel: A Meta-API for Heterogeneous Knowledge Platforms
RuleML2015: API4KP Metamodel: A Meta-API for Heterogeneous Knowledge Platforms
 
RuleML2015: Rule-Based Exploration of Structured Data in the Browser
RuleML2015: Rule-Based Exploration of Structured Data in the BrowserRuleML2015: Rule-Based Exploration of Structured Data in the Browser
RuleML2015: Rule-Based Exploration of Structured Data in the Browser
 
RuleML2015: Ontology-Based Multidimensional Contexts with Applications to Qua...
RuleML2015: Ontology-Based Multidimensional Contexts with Applications to Qua...RuleML2015: Ontology-Based Multidimensional Contexts with Applications to Qua...
RuleML2015: Ontology-Based Multidimensional Contexts with Applications to Qua...
 
RuleML2015: Compact representation of conditional probability for rule-based...
RuleML2015:  Compact representation of conditional probability for rule-based...RuleML2015:  Compact representation of conditional probability for rule-based...
RuleML2015: Compact representation of conditional probability for rule-based...
 
RuleML2015: Learning Characteristic Rules in Geographic Information Systems
RuleML2015: Learning Characteristic Rules in Geographic Information SystemsRuleML2015: Learning Characteristic Rules in Geographic Information Systems
RuleML2015: Learning Characteristic Rules in Geographic Information Systems
 
RuleML2015: Using Substitutive Itemset Mining Framework for Finding Synonymou...
RuleML2015: Using Substitutive Itemset Mining Framework for Finding Synonymou...RuleML2015: Using Substitutive Itemset Mining Framework for Finding Synonymou...
RuleML2015: Using Substitutive Itemset Mining Framework for Finding Synonymou...
 
RuleML2015: User Extensible System to Identify Problems in OWL Ontologies and...
RuleML2015: User Extensible System to Identify Problems in OWL Ontologies and...RuleML2015: User Extensible System to Identify Problems in OWL Ontologies and...
RuleML2015: User Extensible System to Identify Problems in OWL Ontologies and...
 

Último

Recombinant DNA technology( Transgenic plant and animal)
Recombinant DNA technology( Transgenic plant and animal)Recombinant DNA technology( Transgenic plant and animal)
Recombinant DNA technology( Transgenic plant and animal)DHURKADEVIBASKAR
 
Boyles law module in the grade 10 science
Boyles law module in the grade 10 scienceBoyles law module in the grade 10 science
Boyles law module in the grade 10 sciencefloriejanemacaya1
 
Natural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsNatural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsAArockiyaNisha
 
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptxUnlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptxanandsmhk
 
GFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxGFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxAleenaTreesaSaji
 
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.aasikanpl
 
Module 4: Mendelian Genetics and Punnett Square
Module 4:  Mendelian Genetics and Punnett SquareModule 4:  Mendelian Genetics and Punnett Square
Module 4: Mendelian Genetics and Punnett SquareIsiahStephanRadaza
 
Biopesticide (2).pptx .This slides helps to know the different types of biop...
Biopesticide (2).pptx  .This slides helps to know the different types of biop...Biopesticide (2).pptx  .This slides helps to know the different types of biop...
Biopesticide (2).pptx .This slides helps to know the different types of biop...RohitNehra6
 
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡anilsa9823
 
Analytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfAnalytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfSwapnil Therkar
 
Behavioral Disorder: Schizophrenia & it's Case Study.pdf
Behavioral Disorder: Schizophrenia & it's Case Study.pdfBehavioral Disorder: Schizophrenia & it's Case Study.pdf
Behavioral Disorder: Schizophrenia & it's Case Study.pdfSELF-EXPLANATORY
 
Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )aarthirajkumar25
 
zoogeography of pakistan.pptx fauna of Pakistan
zoogeography of pakistan.pptx fauna of Pakistanzoogeography of pakistan.pptx fauna of Pakistan
zoogeography of pakistan.pptx fauna of Pakistanzohaibmir069
 
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...jana861314
 
Dashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tanta
Dashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tantaDashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tanta
Dashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tantaPraksha3
 
The Black hole shadow in Modified Gravity
The Black hole shadow in Modified GravityThe Black hole shadow in Modified Gravity
The Black hole shadow in Modified GravitySubhadipsau21168
 
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsHubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsSérgio Sacani
 
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...Sérgio Sacani
 

Último (20)

Recombinant DNA technology( Transgenic plant and animal)
Recombinant DNA technology( Transgenic plant and animal)Recombinant DNA technology( Transgenic plant and animal)
Recombinant DNA technology( Transgenic plant and animal)
 
Boyles law module in the grade 10 science
Boyles law module in the grade 10 scienceBoyles law module in the grade 10 science
Boyles law module in the grade 10 science
 
Natural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsNatural Polymer Based Nanomaterials
Natural Polymer Based Nanomaterials
 
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptxUnlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
 
GFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxGFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptx
 
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
 
Module 4: Mendelian Genetics and Punnett Square
Module 4:  Mendelian Genetics and Punnett SquareModule 4:  Mendelian Genetics and Punnett Square
Module 4: Mendelian Genetics and Punnett Square
 
Biopesticide (2).pptx .This slides helps to know the different types of biop...
Biopesticide (2).pptx  .This slides helps to know the different types of biop...Biopesticide (2).pptx  .This slides helps to know the different types of biop...
Biopesticide (2).pptx .This slides helps to know the different types of biop...
 
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡
 
Analytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfAnalytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdf
 
Behavioral Disorder: Schizophrenia & it's Case Study.pdf
Behavioral Disorder: Schizophrenia & it's Case Study.pdfBehavioral Disorder: Schizophrenia & it's Case Study.pdf
Behavioral Disorder: Schizophrenia & it's Case Study.pdf
 
Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )
 
zoogeography of pakistan.pptx fauna of Pakistan
zoogeography of pakistan.pptx fauna of Pakistanzoogeography of pakistan.pptx fauna of Pakistan
zoogeography of pakistan.pptx fauna of Pakistan
 
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
 
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
 
Dashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tanta
Dashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tantaDashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tanta
Dashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tanta
 
The Black hole shadow in Modified Gravity
The Black hole shadow in Modified GravityThe Black hole shadow in Modified Gravity
The Black hole shadow in Modified Gravity
 
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsHubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
 
Engler and Prantl system of classification in plant taxonomy
Engler and Prantl system of classification in plant taxonomyEngler and Prantl system of classification in plant taxonomy
Engler and Prantl system of classification in plant taxonomy
 
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
 

RuleML2015: Rule Generalization Strategies in Incremental Learning of Disjunctive Concepts

  • 1. Rule Generalization Strategies in Incremental Learning of Disjunctive Concepts Stefano Ferilli, Andrea Pazienza, Floriana Esposito stefano.ferilli@uniba.it Dipartimento di Informatica Centro Interdipartimentale per la Logica e sue Applicazioni Università di Bari 9th International Web Rule Symposium (RuleML) August 2-5, 2015 – Berlin, Germany
  • 2. Overview ● Introduction & Motivation ● Generalization Algorithm ● Selection Strategies ● Evaluation ● Conclusions & Future Work
  • 3. Introduction ● Symbolic knowledge representations ● Mandatory for applications that – Reproduce the human inferential behavior – May be required to explain their decisions in human- understandable terms ● 2 kinds of concept definitions – Conjunctive: a single definition accounts for all instances of the concept – Disjunctive: several alternate conjunctive definitions (components) ● Each covers part of the full concept extension ● Psychological studies have established that capturing and dealing with the latter is much harder for humans ● Pervasive and fundamental in most real-world domains
  • 4. Introduction ● Knowledge acquisition bottleneck ● (Symbolic) Machine Learning (ML) systems – Supervised setting: concept definitions inferred from descriptions of valid (positive) or invalid (negative) instances (examples) ● Batch: whole set of examples available (classical setting in ML) – Components learned by progressive coverage strategies – Definitions are immutable ● If additional examples are provided, learning must start from scratch considering the extended set of examples ● Incremental: new examples may be provided after a tentative definition is already available – Components emerge as long as they are found – Definitions may be changed/refined if wrong
  • 5. Motivations ● Incremental approach – If the available concept definition cannot properly account for a new example, it must be refined (revised, changed, modified) so that the new version properly accounts for both the old and the new examples – Progressive covering strategy not applicable ● Issue of disjunctive definitions becomes particularly relevant – When many components can be refined, there is no unique way for determining which one is most profitably refined – Refining different components results in different updated definitions, that become implicit constraints on how the definition itself may evolve when additional examples will become available in the future ● The learned model depends – on the order in which the examples are provided – on the choice of the component to be refined at each step
  • 6. Motivations ● Abstract Diagnosis: Identification of the part of the theory that misclassifies the example – Tricky in the case of disjunctive concepts ● Several alternate conjunctive definitions are available – If a positive example is not covered, no component of the current definition accounts for it (omission error) ● All candidate to generalization – Generalizing all components, each component would account alone for all positive examples ● Contradiction: the concept is conjunctive ● Over-generalization: the theory would be more prone to covering forthcoming negative examples – Problem not present in batch learning
  • 7. Motivations ● Problem – A single component of a disjunctive concept is to be generalized ● Guided solutions may improve effectiveness and efficiency of the overall outcome compared to a random strategy ● Objective – Propose and evaluate different strategies for determining the order in which the components should be considered for generalization ● If the generalization of a component fails, generalization of the next component in the ordering is attempted
  • 8. Motivations ● Questions: – what sensible strategies can be defined? – what are their expected pros and cons? – what is their effect on the quality of the theory? – what about their consequences on the effectiveness and efficiency of the learning process? ● Starting point – InTheLEx (Incremental Theory Learner from Examples) ● fully incremental ● can learn disjunctive concept definitions ● refinement strategy can be tuned to suitably adapt its behavior
  • 9. InTheLEx ● Learns hierarchical theories from positive and negative examples ● Fully incremental – May start from an empty theory and from the first available example ● Necessary in most real-world application domains ● DatalogOI – Concept definitions and examples expressed as rules ● Example: example :- observation ● Rule: concept :- conjunctive definition – Disjunctive concepts: several rules for the same concept
  • 10. InTheLEx: Representation – Theory that defines a disjunctive concept (4 components) ● ball(A) :- weight_medium(A), air_filled(A), has_patches(A), horizontal_diameter(A,B), vertical_diameter(A,C), equal(B,C). %generic ● ball(A) :- weight_medium(A), air_filled(A), has_patches(A,B), horizontal_diameter(A,B), vertical_diameter(A,C), larger(B,C). %rugby ● ball(A) :- weight_heavy(A), has_holes(A), horizontal_diameter(A,B), vertical_diameter(A,C), equal(B,C). %bowling ● ball(A) :- weight_light(A), regular_shape(A), horizontal_diameter(A,B), vertical_diameter(A,C), equal(B,C). %small – Examples: ● ball(e) :- weight_medium(e), has_patches(e), air_filled(e), made_of_leather(e), horizontal_diameter(e,he), vertical_diameter(e,ve), equal(he,ve). %soccer Etrusco FIFA World Cup 1990 ● neg(ball(s1)) :- weight_light(s1), made_of_snow(s1), irregular_shape(s1), horizontal_diameter(s1,hs1), vertical_diameter(s1,vs1), smaller(hs1,vs1). %snowball ● neg(ball(s2)) :- weight_light(s2), made_of_paper(s2), horizontal_diameter(s2,hs2), vertical_diameter(s2,vs2), larger(hs2,vs2). %spitball
  • 11. InTheLEx: Theory Revision ● Logic theory revision process – Given a new example ● No effect on the theory if – negative and not covered ● not predicted by the theory to belong to the concept – positive and covered ● predicted by the theory to belong to the concept ● In all the other cases, the theory needs to be revised – Positive example not covered  generalization of the theory – Negative example covered  specialization of the theory – Refinements (generalizations or specializations) must preserve correctness with respect to the entire set of currently available examples ● If no candidate refinement fulfills this requirement, the specific problematic example is stored as an exception
  • 12. InTheLEx: Generalization – Procedure Generalize (E: positive example, T: theory, M: negative examples); ● L := list of the rules in the definition of E's concept while not generalized and L   do – Select from L a rule C for generalization – L' := generalize(C,E) (* list of generalizations *) – while not generalized and L'   do ● Select next best generalization C' from L' ● if (T {C}  {C'} is consistent wrt M then ● Implement C' in T – Remove C from L ● if not generalized then – C' := E with constants turned into variables – if (T {C}  {C'} is consistent wrt M then ● Implement C' in T – else ● Implement E in T as an exception
  • 13. InTheLEx: Generalization – Comments ● Due to theoretical and implementation details, the generalization operator used might return several incomparable generalizations ● Implementation of the theoretical generalization operator would be computationally infeasible, even for relatively small rules – Similarity-based approximation ● Experiments have shown that it comes very close, and often catches, least general generalizations ● First example of a new concept – First rule rule added for that concept ● Initial tentative conjunctive definition of the concept ● Conjunctive definition turns out to be insufficient – Second rule added for that concept ● The concept becomes disjunctive ● Subsequent addition of rules for that concept – Extend the ‘disjunctiveness’ of the concept
  • 14. Clause Selection Strategy ● 5 strategies for determining the order in which the components of a disjunctive concept definition are to be considered for generalization – Each component in the ordering considered only after generalization attempts have failed on all previous components ● Initial components have more chances to be generalized – No direct connection between age and length of a rule ● Older rules might have had more chances of refinement ● Whether this means that they are also shorter (i.e., more general) mainly depends on – Ranking strategy – Specific examples that are encountered and on their order ● Not controllable in a real-world setting
  • 15. Clause Selection Strategy ● O: Older elements first – Same order as they were added to the theory ● The most straightforward. A sort of baseline ● Static: position of each component in the processing order fixed when component is added – Generalizations are monotonic (progressively remove constraints) ● Strategy expected to yield very refined (short, more human-readable and understandable) initial components and very raw (long) final ones – After several refinements, it is likely that initial components have reached a nearly final and quite stable form ● All attempts to further refine them are likely to fail ● The computational time spent in these attempts, albeit presumably not huge, will be wasted ● Runtime expected to grow as long as the life of the theory proceeds
  • 16. Clause Selection Strategy ● N: Newer elements first – Reverse order as they were added to the theory ● Also quite straightforward ● Static, but not obvious to foresee what will be the shape and evolution of the components – Immediately after the addition of a new component, it will undergo a generalization attempt at the first non-covered positive example ● ‘average’ level of generality in the definition expected to be less than in the previous option ● There should be no completely raw components in the definition ● Many chances that such an attempt is successful for any example, but the resulting generalization might leverage features that might be not very related to the correct concept definition
  • 17. Clause Selection Strategy ● L: Longer elements first – Decreasing number of conjuncts ● Specifically considers the level of refinement – Low variance in degree of refinement among components expected ● Can be considered as an evolution of N – Not just the most recently added component is favored for generalization ● The more conjuncts in a component, the more specialized the component – More room for generalization ● Avoid waste of time trying to generalize very refined rules that would hardly yield consistent generalizations ● On the other hand, generalizing a longer rule is expected to take more time than generalizing shorter ones
  • 18. Clause Selection Strategy ● S: Shorter elements first – Increasing number of conjuncts ● Specifically considers the level of refinement – Opposite behavior than L ● May confirm the possible advantage of spending time in trying harder but more promising generalizations versus spending time in trying easier but less promising ones first ● Can be considered as an evolution of O – Tries to generalize first more refined components ● Largest variance in degree of refinement (number of conjuncts in rule premises) among components expected
  • 19. Clause Selection Strategy ● ~: More similar elements first – Decreasing similarity with the uncovered example ● Only content-based strategy – Same similarity as in InTheLEx’s generalization operator ● Disjunctive components  different actualizations of a concept – Small intersection expected between the sets of examples covered by different components ● Similarity assessment may allow to identify the appropriate component to be generalized for a given example – Odd generalizations for mismatched component-example ● Coverage and generalization problems ● Bad theory, inefficient refinements – One might expect that over-generalization is avoided – Generalization more easily computed, but overhead to compute the similarity ● Does the improvement compensate the overhead?
  • 20. Evaluation ● Real-world dataset: Scientific papers – 353 layout descriptions of first pages – 4 classes: Elsevier journals, SVLN, JMLR, MLJ ● Classification: learn definitions for these classes ● Understanding: the significant components in the papers – Title, Author, Abstract, Keywords ● First-Order Logic representation needed to express spatial relationships among the page components ● Complex dataset – Some layout styles are quite similar – 67920 atoms in observations ● avg per observation >192 atoms, some >400 atoms – Much indeterminacy ● Membership relation of layout components to pages
  • 21. Evaluation: Parameters ● Qualitative – # comp in the disjunctive concept definition ● Less components yield a more compact theory, which does not necessarily provide for greater accuracy – avg length of components ● More conjuncts, more specific -and less refined- concept – # exc negative exceptions ● More exceptions, worse theory ● Quantitative – acc (accuracy) ● Prediction capabilities of the theory on test examples – time needed to carry out the learning task ● Efficiency (computational cost) for the different ranking strategies
  • 22. Evaluation ● Incremental approach justified – New instances of documents continuously available in time ● Comparison of all strategies – Random not tried ● O or N are somehow random – Just append definitions as long as they are generated, without any insight ● 10-fold cross-validation procedure – Classification task used to check in detail the behavior of the different strategies – Understanding task used to assess the statistical significance of the difference in performance between different strategies
  • 23. Evaluation: Classification ● Useful results only for MLJ and SVLN – Elsevier and JMLR: always single-rule definitions ● Ranking approach not applicable – Examples for Elsevier and JMLR still played a role as negative examples for the other classes – Some expectations confirmed ● Runtime: N always best (often the first generalization attempt succeeds); ~ worst (need for computing the similarity of each component and the example) ● Number of exceptions: ~ always best (improved selection of components for generalization); S also good ● Aggregated indicator: N always wins – Sum of ranking positions for the different parameters (the smaller, the better)
  • 25. Evaluation: Classification – Rest of behavior somehow mixed ● SVLN: much less variance than in MLJ – Definition quite clear and examples quite significant? ● MLJ: Impact of the ranking strategies much clearer – Substantial agreement between quality-related indicators: for each approach, either all tend to be good (as in ~) or all tend to be bad (as in S and O) ● Interesting indications from single folds – 3: peak in runtime and number of exceptions for S and O ● runtime a consequence of the unsuccessful search for specializations, that in turn may have some connection with the quality of the theory ● S is a kind of evolution of O – 8: accuracy increases from 82% to 94% for ~ and L ● Content-based approach improves quality of the theory in difficult situations
  • 26. Evaluation: Understanding ● Strategy on the row equal (=), better (+) or worse (–) than the one on the column ● Best strategy in bold
  • 27. Evaluation: Understanding ● Quite different, albeit run on the same data – When the difference is significant, in general analogous behavior of L and ~ for accuracy (which is greater), number of components and number of negative exceptions. As expected, longer runtime for ~ – Also O and S have in general an analogous behavior, but do not reach as good results as L and ~ – N not outstanding for performance, but better than O (the baseline) for all parameters except runtime – On the classification task, average length of components using L significantly larger than all the others ● Returns more balanced components but more accuracy and less negative exceptions
  • 28. Conclusions & Future Work ● Disjunctive concept definitions tricky – Each component covers a subset of positive examples, ensuring consistency with all negative examples ● In incremental learning, when a new positive example is not recognized by the current theory, one component must be generalized – Omission error (no specific component responsible) ● The system must decide the order in which the elements are to be considered for trying a generalization – 5 strategies proposed ● The outcomes confirm some of the expectations for the various strategies, but we need – More extensive experimentation to have confirmations and additional details – Identification of further strategies and refinement of the proposed ones