SlideShare una empresa de Scribd logo
1 de 137
Descargar para leer sin conexión
Deep learning
A primer for the curious developer

Uwe Friedrichsen & Dr. Shirin Glander –codecentric AG – 2018
@ufried

Uwe Friedrichsen

uwe.friedrichsen@codecentric.de
@ShirinGlander

Dr. Shirin Glander

shirin.glander@codecentric.de
Why should I care about Deep Learning?
Deep learning has the potential to affect white collar workers (including IT)
in a similar way as robots affected blue collar workers.
What is Deep Learning?

Some success stories
What is Deep Learning?

A rough classification
AI

Artificial
Intelligence
ML

Machine
Learning
RL

Representational
Learning
DL

Deep
Learning
Traditional AI




Focus on problems that are ...
•  ... hard for humans
•  ... straightforward for computers
•  ... can be formally described
Deep Learning




Focus on problems that are ...
•  ... intuitive for humans
•  ... difficult for computers
(hard to be described formally)
•  ... best learnt from experience
Where does Deep Learning come from?
General evolution


•  Two opposed forces
•  Recreation of biological neural processing
•  Abstract mathematical models (mostly linear algebra)
•  Results in different models and algorithms
•  No clear winner yet
Cybernetics (ca. 1940 - 1960)

•  ADALINE, Perceptron
•  Linear models, typically no hidden layers
•  Stochastic Gradient Descent (SGD)
•  Limited applicability
•  E.g., ADALINE could not learn XOR
•  Resulted in “First winter of ANN” (Artificial Neural Networks)
Connectionism (ca. 1980 - 1990)

•  Neocognitron
•  Non-linear models, distributed feature representation
•  Backpropagation
•  Typically 1, rarely more hidden layers
•  First approaches of sequence modeling
•  LSTM (Long short-term memory) in 1997
•  Unrealistic expectations nurtured by ventures
•  Resulted in “Second winter of ANN”
Deep Learning (ca. 2006 -)


•  Improved algorithms, advanced computing power
•  Enabled training much larger and deeper networks
•  Enabled training much larger data sets
•  Typically several to many hidden layers
•  Overcame the “feature extraction dilemma”
What is Deep Learning used for?
Deep Learning application areas




•  Classification (incl. missing inputs)
•  Regression (value prediction)
•  Function prediction
•  Density estimation
•  Structured output (e.g., translation)





•  Anomaly detection
•  Synthesis and sampling
•  Denoising
•  Compression (dimension reduction)
•  ...
How does Deep Learning work?

A first (scientifically inspired) approach
„A computer program is said to learn
•  from experience E
•  with respect to some class of tasks T
•  and performance measure P
if its performance at tasks in T,
as measured by P,
improves with experience E.”

-- T. Mitchell, Machine Learning, p. 2, McGraw Hill (1997)
Supervised learning,
unsupervised learning,
reinforcement learning, ...
Too difficult to solve
with fixed programs
designed by humans
Accuracy vs. error rate,
training vs. test set, ...
Err ...
Hmm ...
Well ...
I don’t get it!
How does Deep Learning work?

A second (more down-to-earth) approach
Operating
principle
Training
Network
types
Deep
Learning
Deep
Learning
Operating
principle
Training
Network
types
Structure
Behavior
Weight
Operation
Neuron
Data
CNN
Types
Challenges
Quality
measure
RNN
 LSTM
Auto-
encoder
GAN
MLP
Training
set
Cost
function
Transfer
learning
Regulari-
zation
Layer
Connection
Hyper-
parameter
Activation
function
Reinforce-
ment
Unsuper-
vised
Supervised
Stochastic
gradient
descent
Back-
propagation
Under-/
Overfitting
Validation/
Test set
Optimization
procedure
Deep
Learning
Operating
principle
Training
Network
types
Structure
Behavior
Operating
principle
Structure
Behavior
Operating
principle
Operating
principle
Structure
Behavior
Neuron
Neuron

•  Design inspired by biological neurons
•  One or more inputs
•  Processing (and state storage) unit
•  One or more outputs
•  In practice often implemented as tensor transformations
•  Relevance of internal state depends on network type
•  Usually negligible for feed-forward networks
•  Usually relevant for recurrent networks
Neuron

Processing

(+ State)
Output(s)
Input(s)
...
...
Layer
Operating
principle
Structure
Behavior
Neuron
Layer

•  Neurons typically organized in layers
•  Input and output layer as default
•  Optionally one or more hidden layer
•  Layer layout can have 1-n dimensions
•  Neurons in different layers can have different properties
•  Different layers responsible for different (sub-)tasks
Output layer
Input layer
...
N
1
2
Hidden layer(s)
...
Connection
Operating
principle
Structure
Behavior
Neuron
Layer
Connection

•  Usually connect input and output tensor in a 1:1 manner
•  Connect between layers (output layer N-1 à input layer N)
•  Layers can be fully or partially (sparsely) connected
•  RNNs also have backward and/or self connections
•  Some networks have connections between neurons
of the same layer (e.g., Hopfield nets, Boltzmann machines)
Input tensor(s)
Output tensor(s)
Weight
Operating
principle
Structure
Behavior
Neuron
Layer
Connection
Weight

•  (Logically) augments a connection
•  Used to amplify or dampen a signal sent over a connection
•  The actual “memory” of the network
•  The “right” values of the weights are learned during training
•  Can also be used to introduce a bias for a neuron
•  By connecting it to an extra neuron that constantly emits 1
W
 Weight
Operation
Operating
principle
Structure
Behavior
Neuron
Layer
Weight
Connection
Input tensor(s)
Output tensor(s)
Step 1

•  For each neuron of input layer
•  Copy resp. input tensor’s value to neuron’s input
•  Calculate state/output using activation function
(typically linear function, passing value through)
Step 2-N

•  For each hidden layer and output layer in their order
•  For each neuron of the layer
•  Calculate weighted sum on inputs
•  Calculate state/output using activation function
(see examples later)
Final step

•  For each neuron of output layer
•  Copy neuron’s output to resp. output tensor’s value
Input tensor(s)
Output tensor(s)
Step 1
Final step
Step 2-N
•  Default update procedure (most widespread)
•  All neuron per layer in parallel
•  Different update procedures exist
•  E.g., some Hopfield net implementations
randomly pick neurons for update
Activation
function
Operating
principle
Structure
Behavior
Neuron
Layer
Weight
Connection
Operation
Linear function

•  Easy to handle
•  Cannot handle
non-linear problems
Logistic sigmoid function

•  Very widespread
•  Delimits output to [0, 1]
•  Vanishing gradient
problem
Hyperbolic tangent

•  Very widespread
•  Delimits output to [-1, 1]
•  Vanishing gradient
problem
Rectified linear unit (ReLU)

•  Easy to handle
•  No derivative in 0
•  Dying ReLU problem
•  Can be mitigated, e.g.,
by using leaky ReLU
Softplus

•  Smooth approximation
of ReLU
•  ReLU usually performs
better
•  Thus, use of softplus
usually discouraged
Hyper-
parameter
Operating
principle
Structure
Behavior
Neuron
Layer
Weight
Connection
Operation
Activation
function
Hyperparameter


•  Influence network and algorithm behavior
•  Often influence model capacity
•  Not learned, but usually manually optimized
•  Currently quite some research interest in
automatic hyperparameter optimization
Examples

•  Number of hidden layers
•  Number of hidden units
•  Learning rate
•  Number of clusters
•  Weight decay coefficient
•  Convolution kernel width
•  ...
Training
Deep
Learning
Operating
principle
Network
types
Structure
Behavior
Weight
Operation
Neuron
Layer
Connection
Hyper-
parameter
Activation
function
Quality
measure
Training
Cost function
Training
Quality
measure
Cost function (a.k.a. loss function)

•  Determines distance from optimal performance
•  Mean squared error as simple (and widespread) example
Cost function (a.k.a. loss function)

•  Determines distance from optimal performance
•  Mean squared error as simple (and widespread) example
•  Often augmented with regularization term
for better generalization (see challenges)
Optimization
procedure
Training
Quality
measure
Cost function
Training
Quality
measure
Stochastic
gradient
descent
Cost function
Optimization
procedure
Stochastic gradient descent

•  Direct calculation of minimum often not feasible
•  Instead stepwise “descent” using the gradient
à Gradient descent
Stochastic gradient descent

•  Direct calculation of minimum often not feasible
•  Instead stepwise “descent” using the gradient
à Gradient descent
•  Not feasible for large training sets
•  Use (small) random sample of training set per iteration
à Stochastic gradient descent (SGD)
Stochastic gradient descent
Gradient
Direction
Steepness
x
Stochastic gradient descent
x
ε * gradient
x’
Learning
rate ε
Training
Quality
measure
Stochastic
gradient
descent
 Back-
propagation
Cost function
Optimization
procedure
Backpropagation

•  Procedure to calculate new weights based on loss function
Depends on
cost function
Depends on
activation function
Depends on
input calculation
Backpropagation

•  Procedure to calculate new weights based on loss function
•  Usually “back-propagated” layer-wise
•  Most widespread optimization procedure
Depends on
cost function
Depends on
activation function
Depends on
input calculation
Data
Training
Quality
measure
Stochastic
gradient
descent
 Back-
propagation
Cost function
Optimization
procedure
Training set
Validation/
Test set
Data
Training
Quality
measure
Stochastic
gradient
descent
 Back-
propagation
Cost function
Optimization
procedure
Data set

•  Consists of examples (a.k.a. data points)
•  Example always contains input tensor
•  Sometimes also contains expected output tensor
(depending on training type)
•  Data set usually split up in several parts
•  Training set – optimize accuracy (always used)
•  Test set – test generalization (often used)
•  Validation set – tune hyperparameters (sometimes used)
Data
Types
Training
Quality
measure
Stochastic
gradient
descent
 Back-
propagation
Training set
Validation/
Test set
Cost function
Optimization
procedure
Supervised
Data
Types
Training
Quality
measure
Stochastic
gradient
descent
 Back-
propagation
Training set
Validation/
Test set
Cost function
Optimization
procedure
Supervised learning

•  Typically learns from a large, yet finite set of examples
•  Examples consist of input and output tensor
•  Output tensor describes desired output
•  Output tensor also called label or target
•  Typical application areas
•  Classification
•  Regression and function prediction
•  Structured output problems
Unsupervised
Data
Types
Supervised
Training
Quality
measure
Stochastic
gradient
descent
 Back-
propagation
Training set
Validation/
Test set
Cost function
Optimization
procedure
Unsupervised learning

•  Typically learns from a large, yet finite set of examples
•  Examples consist of input tensor only
•  Learning algorithm tries to learn useful properties of the data
•  Requires different type of cost functions
•  Typical application areas
•  Clustering, density estimations
•  Denoising, compression (dimension reduction)
•  Synthesis and sampling
Reinforcement
Data
Types
Supervised
Training
Quality
measure
Unsupervised
Stochastic
gradient
descent
 Back-
propagation
Training set
Validation/
Test set
Cost function
Optimization
procedure
Reinforcement learning

•  Continuously optimizes interaction with an environment
based on reward-based learning
Agent
Environment
State t
 Reward t
State t+1
 Reward t+1
Action t
Reinforcement learning

•  Continuously optimizes interaction with an environment
based on reward-based learning
•  Goal is selection of action with highest expected reward
•  Takes (discounted) expected future rewards into account
•  Labeling of examples replaced by reward function
•  Can continuously learn à data set can be infinite
•  Typically used to solve complex tasks in (increasingly)
complex environments with (very) limited feedback
Challenges
Data
Types
Supervised
Training
Quality
measure
Unsupervised
Reinforcement
Stochastic
gradient
descent
 Back-
propagation
Training set
Validation/
Test set
Cost function
Optimization
procedure
Data
Types
Supervised
Training
Quality
measure
Unsupervised
Reinforcement
Stochastic
gradient
descent
 Back-
propagation
Under-/
Overfitting
Training set
Validation/
Test set
Cost function
Challenges
Optimization
procedure
Underfitting and Overfitting

•  Training error describes how good training data is learnt
•  Test error is an indicator for generalization capability
•  Core challenge for all machine learning type algorithms
1.  Make training error small
2.  Make gap between training and test error small
•  Underfitting is the violation of #1
•  Overfitting is the violation of #2
Good fit
Underfitting
 Overfitting
Training data
 Test data
Underfitting and Overfitting



•  Under- and overfitting influenced by model capacity
•  Too low capacity usually leads to underfitting
•  Too high capacity usually leads to overfitting
•  Finding the right capacity is a challenge
Data
Types
Supervised
Training
Quality
measure
Unsupervised
Reinforcement
Stochastic
gradient
descent
 Back-
propagation
Under-/
Overfitting
Training set
Validation/
Test set
Cost function
Regularization
Challenges
Optimization
procedure
Regularization

•  Regularization is a modification applied to learning algorithm
•  to reduce the generalization error
•  but not the training error
•  Weight decay is a typical regularization measure
Data
Types
Supervised
Training
Quality
measure
Unsupervised
Reinforcement
Stochastic
gradient
descent
 Back-
propagation
Under-/
Overfitting
Transfer
learning
Training set
Validation/
Test set
Cost function
Regularization
Challenges
Optimization
procedure
Transfer learning


•  How to transfer insights between related tasks
•  E.g., is it possible to transfer knowledge gained while training
to recognize cars on the problem of recognizing trucks?
•  General machine learning problem
•  Subject of many research activities
Network
types
Deep
Learning
Operating
principle
Training
Structure
Behavior
Weight
Operation
Neuron
Data
Types
Challenges
Quality
measure
Training
set
Cost
function
Transfer
learning
Regulari-
zation
Layer
Connection
Hyper-
parameter
Activation
function
Reinforce-
ment
Unsuper-
vised
Supervised
Stochastic
gradient
descent
Back-
propagation
Under-/
Overfitting
Validation/
Test set
Optimization
procedure
MLP

Multilayer
Perceptron
Network
types
Multilayer perceptron (MLP)

•  Multilayer feed-forward networks
•  “Vanilla” neural networks
•  Typically used for
•  Function approximation
•  Regression
•  Classification
Image source: https://deeplearning4j.org
CNN

Convolutional
Neural Network
Network
types
MLP

Multilayer
Perceptron
Convolutional neural network (CNN)

•  Special type of MLP for image processing
•  Connects convolutional neuron only with receptive field
•  Advantages
•  Less computing
power required
•  Often even better
recognition rates
•  Inspired by organization of visual cortex
Image source: https://deeplearning4j.org
RNN

Recurrent
Neural Network
Network
types
MLP

Multilayer
Perceptron
CNN

Convolutional
Neural Network
Recurrent neural network (RNN)

•  Implements internal feedback loops
•  Provides a temporal memory
•  Typically used for
•  Speech recognition
•  Text recognition
•  Time series processing
Image source: https://deeplearning4j.org
LSTM

Long
Short-Term
Memory
Network
types
MLP

Multilayer
Perceptron
CNN

Convolutional
Neural Network
RNN

Recurrent
Neural Network
Long short-term memory (LSTM)

•  Special type of RNN
•  Uses special LSTM units
•  Can implement very long-term memory
while avoiding the vanishing/exploding
gradient problem
•  Same application areas as RNN
Image source: https://deeplearning4j.org
Auto-
encoder
Network
types
MLP

Multilayer
Perceptron
CNN

Convolutional
Neural Network
RNN

Recurrent
Neural Network
LSTM

Long
Short-Term
Memory
Autoencoder
•  Special type of MLP
•  Reproduces input at output layer
•  Consists of encoder and decoder
•  Usually configured undercomplete
•  Learns efficient feature codings
•  Dimension reduction (incl. compression)
•  Denoising
•  Usually needs pre-training for not only
reconstructing average of training set
Image source: https://deeplearning4j.org
GAN

Generative
Adversarial
Networks
Network
types
MLP

Multilayer
Perceptron
CNN

Convolutional
Neural Network
RNN

Recurrent
Neural Network
Auto-
encoder
LSTM

Long
Short-Term
Memory
Generative adversarial networks (GAN)
•  Consists of two (adversarial) networks
•  Generator creating fake images
•  Discriminator trying to identify
fake images
•  Typically used for
•  Synthesis and sampling
(e.g., textures in games)
•  Structured output with variance (e.g., variations of a design or voice generation)
•  Probably best known for creating fake celebrity images
Image source: https://deeplearning4j.org
Deep
Learning
Operating
principle
Training
Network
types
Structure
Behavior
Weight
Operation
Neuron
Data
CNN
Types
Challenges
Quality
measure
RNN
 LSTM
Auto-
encoder
GAN
MLP
Training
set
Cost
function
Transfer
learning
Regulari-
zation
Layer
Connection
Hyper-
parameter
Activation
function
Reinforce-
ment
Unsuper-
vised
Supervised
Stochastic
gradient
descent
Back-
propagation
Under-/
Overfitting
Validation/
Test set
Optimization
procedure
How does Deep Learning feel in practice?
What issues might I face if diving deeper?
Issues you might face

•  Very fast moving research domain
•  You need the math. Really!
•  How much data do you have?
•  GDPR: Can you explain the decision of your network?
•  Meta-Learning as the next step
•  Monopolization of research and knowledge
Wrap-up
Wrap-up

•  Broad, diverse topic
•  Very good library support and more
•  Very active research topic
•  No free lunch
•  You need the math!

à Exciting and important topic – become a part of it!
References

•  I. Goodfellow, Y. Bengio, A. Courville, ”Deep learning",
MIT press, 2016, also available via https://www.deeplearningbook.org
•  C. Perez, “The Deep Learning AI Playbook”,
Intuition Machine Inc., 2017
•  F. Chollet, "Deep Learning with Python",
Manning Publications, 2017
•  OpenAI, https://openai.com
•  Keras, https://keras.io
•  Deep Learning for Java, https://deeplearning4j.org/index.html
•  Deep Learning (Resource site), http://deeplearning.net
@ShirinGlander

Dr. Shirin Glander

shirin.glander@codecentric.de
@ufried

Uwe Friedrichsen

uwe.friedrichsen@codecentric.de

Más contenido relacionado

La actualidad más candente

An overview of gradient descent optimization algorithms
An overview of gradient descent optimization algorithms An overview of gradient descent optimization algorithms
An overview of gradient descent optimization algorithms Hakky St
 
Hillclimbing search algorthim #introduction
Hillclimbing search algorthim #introductionHillclimbing search algorthim #introduction
Hillclimbing search algorthim #introductionMohamed Gad
 
Data Structure and Algorithms.pptx
Data Structure and Algorithms.pptxData Structure and Algorithms.pptx
Data Structure and Algorithms.pptxSyed Zaid Irshad
 
Optimization for Deep Learning
Optimization for Deep LearningOptimization for Deep Learning
Optimization for Deep LearningSebastian Ruder
 
Capter10 cluster basic : Han & Kamber
Capter10 cluster basic : Han & KamberCapter10 cluster basic : Han & Kamber
Capter10 cluster basic : Han & KamberHouw Liong The
 
An Introduction to Supervised Machine Learning and Pattern Classification: Th...
An Introduction to Supervised Machine Learning and Pattern Classification: Th...An Introduction to Supervised Machine Learning and Pattern Classification: Th...
An Introduction to Supervised Machine Learning and Pattern Classification: Th...Sebastian Raschka
 
What Is Dynamic Programming? | Dynamic Programming Explained | Programming Fo...
What Is Dynamic Programming? | Dynamic Programming Explained | Programming Fo...What Is Dynamic Programming? | Dynamic Programming Explained | Programming Fo...
What Is Dynamic Programming? | Dynamic Programming Explained | Programming Fo...Simplilearn
 
17. Java data structures trees representation and traversal
17. Java data structures trees representation and traversal17. Java data structures trees representation and traversal
17. Java data structures trees representation and traversalIntro C# Book
 
Lec 5 uncertainty
Lec 5 uncertaintyLec 5 uncertainty
Lec 5 uncertaintyEyob Sisay
 
Adversarial search with Game Playing
Adversarial search with Game PlayingAdversarial search with Game Playing
Adversarial search with Game PlayingAman Patel
 
Meta-Learning with Memory Augmented Neural Networks
Meta-Learning with Memory Augmented Neural NetworksMeta-Learning with Memory Augmented Neural Networks
Meta-Learning with Memory Augmented Neural Networks홍배 김
 
Recursion - Algorithms and Data Structures
Recursion - Algorithms and Data StructuresRecursion - Algorithms and Data Structures
Recursion - Algorithms and Data StructuresPriyanka Rana
 
Linear regression, costs & gradient descent
Linear regression, costs & gradient descentLinear regression, costs & gradient descent
Linear regression, costs & gradient descentRevanth Kumar
 
Dynamic programming
Dynamic programmingDynamic programming
Dynamic programmingShakil Ahmed
 
Indexing in Cassandra
Indexing in CassandraIndexing in Cassandra
Indexing in CassandraEd Anuff
 
Regularization in deep learning
Regularization in deep learningRegularization in deep learning
Regularization in deep learningKien Le
 
K means and dbscan
K means and dbscanK means and dbscan
K means and dbscanYan Xu
 
Predicate calculus
Predicate calculusPredicate calculus
Predicate calculusRajendran
 

La actualidad más candente (20)

An overview of gradient descent optimization algorithms
An overview of gradient descent optimization algorithms An overview of gradient descent optimization algorithms
An overview of gradient descent optimization algorithms
 
Hillclimbing search algorthim #introduction
Hillclimbing search algorthim #introductionHillclimbing search algorthim #introduction
Hillclimbing search algorthim #introduction
 
Data Structure and Algorithms.pptx
Data Structure and Algorithms.pptxData Structure and Algorithms.pptx
Data Structure and Algorithms.pptx
 
Optimization for Deep Learning
Optimization for Deep LearningOptimization for Deep Learning
Optimization for Deep Learning
 
Capter10 cluster basic : Han & Kamber
Capter10 cluster basic : Han & KamberCapter10 cluster basic : Han & Kamber
Capter10 cluster basic : Han & Kamber
 
An Introduction to Supervised Machine Learning and Pattern Classification: Th...
An Introduction to Supervised Machine Learning and Pattern Classification: Th...An Introduction to Supervised Machine Learning and Pattern Classification: Th...
An Introduction to Supervised Machine Learning and Pattern Classification: Th...
 
What Is Dynamic Programming? | Dynamic Programming Explained | Programming Fo...
What Is Dynamic Programming? | Dynamic Programming Explained | Programming Fo...What Is Dynamic Programming? | Dynamic Programming Explained | Programming Fo...
What Is Dynamic Programming? | Dynamic Programming Explained | Programming Fo...
 
N queen problem
N queen problemN queen problem
N queen problem
 
17. Java data structures trees representation and traversal
17. Java data structures trees representation and traversal17. Java data structures trees representation and traversal
17. Java data structures trees representation and traversal
 
Lec 5 uncertainty
Lec 5 uncertaintyLec 5 uncertainty
Lec 5 uncertainty
 
Cnn
CnnCnn
Cnn
 
Adversarial search with Game Playing
Adversarial search with Game PlayingAdversarial search with Game Playing
Adversarial search with Game Playing
 
Meta-Learning with Memory Augmented Neural Networks
Meta-Learning with Memory Augmented Neural NetworksMeta-Learning with Memory Augmented Neural Networks
Meta-Learning with Memory Augmented Neural Networks
 
Recursion - Algorithms and Data Structures
Recursion - Algorithms and Data StructuresRecursion - Algorithms and Data Structures
Recursion - Algorithms and Data Structures
 
Linear regression, costs & gradient descent
Linear regression, costs & gradient descentLinear regression, costs & gradient descent
Linear regression, costs & gradient descent
 
Dynamic programming
Dynamic programmingDynamic programming
Dynamic programming
 
Indexing in Cassandra
Indexing in CassandraIndexing in Cassandra
Indexing in Cassandra
 
Regularization in deep learning
Regularization in deep learningRegularization in deep learning
Regularization in deep learning
 
K means and dbscan
K means and dbscanK means and dbscan
K means and dbscan
 
Predicate calculus
Predicate calculusPredicate calculus
Predicate calculus
 

Similar a Deep learning - a primer

Deep Learning Sample Class (Jon Lederman)
Deep Learning Sample Class (Jon Lederman)Deep Learning Sample Class (Jon Lederman)
Deep Learning Sample Class (Jon Lederman)Jon Lederman
 
Visualization of Deep Learning
Visualization of Deep LearningVisualization of Deep Learning
Visualization of Deep LearningYaminiAlapati1
 
EssentialsOfMachineLearning.pdf
EssentialsOfMachineLearning.pdfEssentialsOfMachineLearning.pdf
EssentialsOfMachineLearning.pdfAnkita Tiwari
 
Introduction to Deep learning and H2O for beginner's
Introduction to Deep learning and H2O for beginner'sIntroduction to Deep learning and H2O for beginner's
Introduction to Deep learning and H2O for beginner'sVidyasagar Bhargava
 
DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101Felipe Prado
 
Machine Duping 101: Pwning Deep Learning Systems
Machine Duping 101: Pwning Deep Learning SystemsMachine Duping 101: Pwning Deep Learning Systems
Machine Duping 101: Pwning Deep Learning SystemsClarence Chio
 
Deep learning from a novice perspective
Deep learning from a novice perspectiveDeep learning from a novice perspective
Deep learning from a novice perspectiveAnirban Santara
 
Separating Hype from Reality in Deep Learning with Sameer Farooqui
 Separating Hype from Reality in Deep Learning with Sameer Farooqui Separating Hype from Reality in Deep Learning with Sameer Farooqui
Separating Hype from Reality in Deep Learning with Sameer FarooquiDatabricks
 
V2.0 open power ai virtual university deep learning and ai introduction
V2.0 open power ai virtual university   deep learning and ai introductionV2.0 open power ai virtual university   deep learning and ai introduction
V2.0 open power ai virtual university deep learning and ai introductionGanesan Narayanasamy
 
Facial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional FaceFacial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional FaceTakrim Ul Islam Laskar
 
1. Introduction to deep learning.pptx
1. Introduction to deep learning.pptx1. Introduction to deep learning.pptx
1. Introduction to deep learning.pptxKv Sagar
 
Deep learning: the future of recommendations
Deep learning: the future of recommendationsDeep learning: the future of recommendations
Deep learning: the future of recommendationsBalázs Hidasi
 
Machine learning for IoT - unpacking the blackbox
Machine learning for IoT - unpacking the blackboxMachine learning for IoT - unpacking the blackbox
Machine learning for IoT - unpacking the blackboxIvo Andreev
 
DeepLearningLecture.pptx
DeepLearningLecture.pptxDeepLearningLecture.pptx
DeepLearningLecture.pptxssuserf07225
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learningVishwas Lele
 
Hyperparameter Tuning
Hyperparameter TuningHyperparameter Tuning
Hyperparameter TuningJon Lederman
 

Similar a Deep learning - a primer (20)

Deep Learning Sample Class (Jon Lederman)
Deep Learning Sample Class (Jon Lederman)Deep Learning Sample Class (Jon Lederman)
Deep Learning Sample Class (Jon Lederman)
 
Visualization of Deep Learning
Visualization of Deep LearningVisualization of Deep Learning
Visualization of Deep Learning
 
EssentialsOfMachineLearning.pdf
EssentialsOfMachineLearning.pdfEssentialsOfMachineLearning.pdf
EssentialsOfMachineLearning.pdf
 
Deep learning
Deep learningDeep learning
Deep learning
 
Introduction to Deep learning and H2O for beginner's
Introduction to Deep learning and H2O for beginner'sIntroduction to Deep learning and H2O for beginner's
Introduction to Deep learning and H2O for beginner's
 
DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101DEF CON 24 - Clarence Chio - machine duping 101
DEF CON 24 - Clarence Chio - machine duping 101
 
Machine Duping 101: Pwning Deep Learning Systems
Machine Duping 101: Pwning Deep Learning SystemsMachine Duping 101: Pwning Deep Learning Systems
Machine Duping 101: Pwning Deep Learning Systems
 
Deep learning from a novice perspective
Deep learning from a novice perspectiveDeep learning from a novice perspective
Deep learning from a novice perspective
 
Separating Hype from Reality in Deep Learning with Sameer Farooqui
 Separating Hype from Reality in Deep Learning with Sameer Farooqui Separating Hype from Reality in Deep Learning with Sameer Farooqui
Separating Hype from Reality in Deep Learning with Sameer Farooqui
 
V2.0 open power ai virtual university deep learning and ai introduction
V2.0 open power ai virtual university   deep learning and ai introductionV2.0 open power ai virtual university   deep learning and ai introduction
V2.0 open power ai virtual university deep learning and ai introduction
 
Facial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional FaceFacial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional Face
 
1. Introduction to deep learning.pptx
1. Introduction to deep learning.pptx1. Introduction to deep learning.pptx
1. Introduction to deep learning.pptx
 
tensorflow.pptx
tensorflow.pptxtensorflow.pptx
tensorflow.pptx
 
Deep learning: the future of recommendations
Deep learning: the future of recommendationsDeep learning: the future of recommendations
Deep learning: the future of recommendations
 
Machine learning for IoT - unpacking the blackbox
Machine learning for IoT - unpacking the blackboxMachine learning for IoT - unpacking the blackbox
Machine learning for IoT - unpacking the blackbox
 
DeepLearningLecture.pptx
DeepLearningLecture.pptxDeepLearningLecture.pptx
DeepLearningLecture.pptx
 
AI and Deep Learning
AI and Deep Learning AI and Deep Learning
AI and Deep Learning
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
lecture 01.1.ppt
lecture 01.1.pptlecture 01.1.ppt
lecture 01.1.ppt
 
Hyperparameter Tuning
Hyperparameter TuningHyperparameter Tuning
Hyperparameter Tuning
 

Más de Uwe Friedrichsen

Timeless design in a cloud-native world
Timeless design in a cloud-native worldTimeless design in a cloud-native world
Timeless design in a cloud-native worldUwe Friedrichsen
 
The hitchhiker's guide for the confused developer
The hitchhiker's guide for the confused developerThe hitchhiker's guide for the confused developer
The hitchhiker's guide for the confused developerUwe Friedrichsen
 
Digitization solutions - A new breed of software
Digitization solutions - A new breed of softwareDigitization solutions - A new breed of software
Digitization solutions - A new breed of softwareUwe Friedrichsen
 
Real-world consistency explained
Real-world consistency explainedReal-world consistency explained
Real-world consistency explainedUwe Friedrichsen
 
The 7 quests of resilient software design
The 7 quests of resilient software designThe 7 quests of resilient software design
The 7 quests of resilient software designUwe Friedrichsen
 
Excavating the knowledge of our ancestors
Excavating the knowledge of our ancestorsExcavating the knowledge of our ancestors
Excavating the knowledge of our ancestorsUwe Friedrichsen
 
The truth about "You build it, you run it!"
The truth about "You build it, you run it!"The truth about "You build it, you run it!"
The truth about "You build it, you run it!"Uwe Friedrichsen
 
The promises and perils of microservices
The promises and perils of microservicesThe promises and perils of microservices
The promises and perils of microservicesUwe Friedrichsen
 
Resilient Functional Service Design
Resilient Functional Service DesignResilient Functional Service Design
Resilient Functional Service DesignUwe Friedrichsen
 
Resilience reloaded - more resilience patterns
Resilience reloaded - more resilience patternsResilience reloaded - more resilience patterns
Resilience reloaded - more resilience patternsUwe Friedrichsen
 
DevOps is not enough - Embedding DevOps in a broader context
DevOps is not enough - Embedding DevOps in a broader contextDevOps is not enough - Embedding DevOps in a broader context
DevOps is not enough - Embedding DevOps in a broader contextUwe Friedrichsen
 
Towards complex adaptive architectures
Towards complex adaptive architecturesTowards complex adaptive architectures
Towards complex adaptive architecturesUwe Friedrichsen
 
Conway's law revisited - Architectures for an effective IT
Conway's law revisited - Architectures for an effective ITConway's law revisited - Architectures for an effective IT
Conway's law revisited - Architectures for an effective ITUwe Friedrichsen
 
Microservices - stress-free and without increased heart attack risk
Microservices - stress-free and without increased heart attack riskMicroservices - stress-free and without increased heart attack risk
Microservices - stress-free and without increased heart attack riskUwe Friedrichsen
 
Modern times - architectures for a Next Generation of IT
Modern times - architectures for a Next Generation of ITModern times - architectures for a Next Generation of IT
Modern times - architectures for a Next Generation of ITUwe Friedrichsen
 

Más de Uwe Friedrichsen (20)

Timeless design in a cloud-native world
Timeless design in a cloud-native worldTimeless design in a cloud-native world
Timeless design in a cloud-native world
 
Life after microservices
Life after microservicesLife after microservices
Life after microservices
 
The hitchhiker's guide for the confused developer
The hitchhiker's guide for the confused developerThe hitchhiker's guide for the confused developer
The hitchhiker's guide for the confused developer
 
Digitization solutions - A new breed of software
Digitization solutions - A new breed of softwareDigitization solutions - A new breed of software
Digitization solutions - A new breed of software
 
Real-world consistency explained
Real-world consistency explainedReal-world consistency explained
Real-world consistency explained
 
The 7 quests of resilient software design
The 7 quests of resilient software designThe 7 quests of resilient software design
The 7 quests of resilient software design
 
Excavating the knowledge of our ancestors
Excavating the knowledge of our ancestorsExcavating the knowledge of our ancestors
Excavating the knowledge of our ancestors
 
The truth about "You build it, you run it!"
The truth about "You build it, you run it!"The truth about "You build it, you run it!"
The truth about "You build it, you run it!"
 
The promises and perils of microservices
The promises and perils of microservicesThe promises and perils of microservices
The promises and perils of microservices
 
Resilient Functional Service Design
Resilient Functional Service DesignResilient Functional Service Design
Resilient Functional Service Design
 
Watch your communication
Watch your communicationWatch your communication
Watch your communication
 
Life, IT and everything
Life, IT and everythingLife, IT and everything
Life, IT and everything
 
Resilience reloaded - more resilience patterns
Resilience reloaded - more resilience patternsResilience reloaded - more resilience patterns
Resilience reloaded - more resilience patterns
 
DevOps is not enough - Embedding DevOps in a broader context
DevOps is not enough - Embedding DevOps in a broader contextDevOps is not enough - Embedding DevOps in a broader context
DevOps is not enough - Embedding DevOps in a broader context
 
Production-ready Software
Production-ready SoftwareProduction-ready Software
Production-ready Software
 
Towards complex adaptive architectures
Towards complex adaptive architecturesTowards complex adaptive architectures
Towards complex adaptive architectures
 
Conway's law revisited - Architectures for an effective IT
Conway's law revisited - Architectures for an effective ITConway's law revisited - Architectures for an effective IT
Conway's law revisited - Architectures for an effective IT
 
Microservices - stress-free and without increased heart attack risk
Microservices - stress-free and without increased heart attack riskMicroservices - stress-free and without increased heart attack risk
Microservices - stress-free and without increased heart attack risk
 
Patterns of resilience
Patterns of resiliencePatterns of resilience
Patterns of resilience
 
Modern times - architectures for a Next Generation of IT
Modern times - architectures for a Next Generation of ITModern times - architectures for a Next Generation of IT
Modern times - architectures for a Next Generation of IT
 

Último

A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)wesley chun
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfEnterprise Knowledge
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUK Journal
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsJoaquim Jorge
 

Último (20)

A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 

Deep learning - a primer