SlideShare una empresa de Scribd logo
1 de 29
Descargar para leer sin conexión
Looking into the Black Box-
A Theoretical Insight into
Deep Learning Networks
What is
Deep Learning?
Deep learning is a branch of machine learning which is based on
Artificial Neural Networks. As neural networks mimics the human brain,
so does the deep learning based on neural networks.
Deep learning is a representation learning. The automated formation
of useful representations from data.
There are variety of deep learning networks such as Multilayer
Perceptron (MLP), Autoencoders (AE), Convolution Neural Network
(CNN), Recurrent Neural Network (RNN).
02
03
Artificial Intelligence
M
achine Learning
D
eep Learnin
g
Data Science
04
Why
Deep Learning is
Successful?
Deep learning models are large and deep Artificial Neural Networks. A
neural network (“NN”) can be well presented in a directed acyclic
graph.
The input layer takes in signal vectors; one or multiple hidden layers
process the outputs of the previous layer.
But why does it work now? Why deep learning is successful now than
ever?
05
Understands the
problem & check
Feasibility for
Deep Learning
Test the model’s
Performance
Choose
Deep Learning
Algorithm
Identifies Relevant
Data & prepares it
Training
Algorithm
Architecture of Deep Learning
I
I
I
H
O
H
H
H
H
H
H
H
I - Input layer H - Hidden layer O - Output layer
Deep Learning Model
06
How do data science techniques scale with amount of data?
Performance
Amount of data
Why Deep Learning
Deep learning
Older learning
algorithms
07
Why is
Deep Learning
Successful?
The reason for Deep learning networks success is:
We have a lot more data.
We have much powerful computers.
A large and deep neural network has many layers and many nodes in
each layer, resulting in many parameters to tune. Without enough
data, we cannot learn parameters efficiently. Without powerful
computers, learning would be too slow and insufficient.
08
Why is
Deep Learning
Successful?
Neural networks are either encoders, decoders, or a combination of
both:
Encoders find patterns in raw data to form compact, useful
representations.
Decoders generate high-resolution data from those representations.
The generated data is either new examples or descriptive knowledge.
09
Traditional Pattern Recognition: Fixed/Handcrafted Feature Extractor
Mainstream Pattern Recognition: Unsupervised mid-level features
Deep Learning: Representations are hierarchical and trained
Feature
Extractor
Mid-Level
Features
Low-Level
Features
Feature
Extractor
Trainable
Classifier
Trainable
Classifier
Trainable
Classifier
Mid-Level
Features
High-Level
Features
10
Supervised
Learning
Unsupervised
Learning
Reinforcement
Learning
Feed Forward
Neural Networks
Convolutional
Neural Networks
Recurrent
Neural Networks
Encoder-Decoder
Architectures
Autoencoder
Generative Adversarial
Networks
Networks for Actions,
Values, Policies,
& Models
Types of
Deep Learning Model
11
Feed Forward
Neural Networks
(FFNNs)
FFNNs dating back to 1940s, are networks that don’t have any cycles.
Data passes from input to output in a single pass without any “state
memory”.
Technically, most networks in deep learning can be considered FFNNs,
but usually “FFNN” refers to its simplest variant: a densely-
connected multilayer perceptron (MLP).
Dense encoders are used to map an already compact set of
numbers on the input to a prediction: either a classification (discrete)
or a regression (continuous).
12
Feed Forward Neural Networks
A Few
Numbers
Dense
Encoder
Representation Prediction Prediction
Ground TruthOutputNetworkInput
13
Convolutional
Neural Networks
(CNNs)
CNNs are feed forward neural networks that use a spatial-invariance
trick to efficiently learn local patterns, most commonly, in images.
Spatial-invariance means that a subject's ear in the top left of the
image has the same features as a subject's ear in bottom right of the
image. CNNs share weights across space to make the detection of
subject's ears and other patterns more efficient.
Instead of using only densely-connected layers, they use
convolutional layers (convolutional encoder). These networks are
used for image classification, object detection, video action
recognition, and any data that has some spatial invariance in its
structure.
14
Convolutional Neural Networks
An
Image
Convolutional
Encoder
Representation Prediction Prediction
Ground TruthOutputNetworkInput
15
Recurrent
Neural Networks
(RNNs)
RNNs are networks that have cycles and therefore have “state
memory”. They can be unrolled in time to become feed forward
networks where the weights are shared. Just as CNNs share weights
across “space”, RNNs share weights across “time”. This allows them to
process and efficiently represent patterns in sequential data.
Many variants of RNNs modules have been developed, including LSTMs
and GRUs, to help learn patterns in longer sequences. Applications
include natural language modeling, speech recognition, speech
generation, etc.
16
Recurrent Neural Network
Sequence Recurrent
Encoder Representation Prediction Prediction
Ground TruthOutputNetworkInput
17
Encoder-Decoder
Architectures
FFNNs, CNNs, and RNNs presented in first 3 sections are simply
networks that make a prediction using either a dense encoder,
convolutional encoder, or a recurrent encoder, respectively. These
encoders can be combined or switched depending on the kind of raw
data we’re trying to form a useful representation of.
“Encoder-Decoder” architecture is a higher-level concept that builds
on the encoding step to, instead of making a prediction, generate a
high-dimensional output via a decoding step by upsampling the
compressed representation.
Applications include semantic segmentation, machine translation,
etc.
18
Encoder-Decoder Architectures
Image,
Text,
etc.
Any
Encoder
Representation
Ground TruthNetwork
Any
Decoder
Network Output
Image,
Text,
etc.
Input
Image,
Text,
etc.
19
Autoencoders
Autoencoders are one of the simpler forms of “unsupervised learning”
taking the encoder-decoder architecture and learning to generate an
exact copy of the input data. Since the encoded representation is
much smaller than the input data, the network is forced to learn how
to form the most meaningful representation.
Since the ground truth data comes from the input data, no human
effort is required. In other words, it’s self-supervised.
Applications include unsupervised embeddings, image denoising, etc.
20
21
Autoencoder
Exact copy
of input
Any
Encoder Representation
Ground TruthNetwork
Any
Decoder
Network
Image,
Text,
etc.
Input
Generative
Adversarial
Networks
(GANs)
GANs are a framework for training networks optimized for generating
new realistic samples from a particular representation. In its simplest
form, the training process involves two networks. One network, called
the generator, generates new data instances, trying to fool the other
network, the discriminator, that classifies images as real or fake.
They can generate images from a particular class, the ability to map
images from one domain to another, and an incredible increase in
realism of generated images.
22
Generative Adversarial Networks
Real Image
Generator Fake Image
Ground TruthNetwork
Discriminator
Network
Noise
Input Output
Prediction
Real or Fake
Throw away after training
23
Deep
Reinforcement
Learning
(Deep RL)
Deep RL allows us to apply neural networks in simulated or real-world
environments when sequences of decisions need to be made.
When the learning is done by a neural network, we refer to it as Deep
Reinforcement Learning (Deep RL). There are three types of RL
frameworks: policy-based, value-based, and model-based. The
distinction is what the neural network is tasked with learning.
This includes game playing, robotics , neural architecture search, and
much more.
24
World
State Sample
Any
Encoder
Representation Action
Output
Reward
Ground TruthInput Network
Deep Reinforcement Learning
25
26
Advantages
Best in-class performance
on problems.
Reduces need for
feature engineering.
Eliminates
unnecessary costs.
Identifies defects easily
that are difficult to detect.
27
Applications of
Deep Learning
Models
Automatic Text Generation – Corpus of text is learned and from this
model new text is generated, word-by-word or character-by-
character. Then this model can learn how to spell, punctuate, form
sentences, or it may even capture the style.
Healthcare – Helps in diagnosing various diseases and treating it.
Automatic Machine Translation – Certain words, sentences or
phrases in one language is transformed into another language (Deep
Learning is achieving top results in the areas of text, images).
28
Applications of
Deep Learning
Models
Image Recognition – Recognizes and identifies people and objects in
images as well as to understand content and context. This area is
already being used in Gaming, Retail, Tourism, etc.
Predicting Earthquakes – Teaches a computer to perform viscoelastic
computations which are used in predicting earthquakes.
To assist you with our services
please reach us at
hello@mitosistech.com
www.mitosistech.com
IND: +91-7824035173
US: +1-(415) 251-2064

Más contenido relacionado

La actualidad más candente

Deep learning - what is it and why now?
Deep learning - what is it and why now?Deep learning - what is it and why now?
Deep learning - what is it and why now?Natalia Konstantinova
 
Intro to Deep Learning for Computer Vision
Intro to Deep Learning for Computer VisionIntro to Deep Learning for Computer Vision
Intro to Deep Learning for Computer VisionChristoph Körner
 
101: Convolutional Neural Networks
101: Convolutional Neural Networks 101: Convolutional Neural Networks
101: Convolutional Neural Networks Mad Scientists
 
deeplearning
deeplearningdeeplearning
deeplearninghuda2018
 
Deep learning - Conceptual understanding and applications
Deep learning - Conceptual understanding and applicationsDeep learning - Conceptual understanding and applications
Deep learning - Conceptual understanding and applicationsBuhwan Jeong
 
From neural networks to deep learning
From neural networks to deep learningFrom neural networks to deep learning
From neural networks to deep learningViet-Trung TRAN
 
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...Universitat Politècnica de Catalunya
 
Top 10 deep learning algorithms you should know in
Top 10 deep learning algorithms you should know inTop 10 deep learning algorithms you should know in
Top 10 deep learning algorithms you should know inAmanKumarSingh97
 
Building distributed deep learning engine
Building distributed deep learning engineBuilding distributed deep learning engine
Building distributed deep learning engineGuangdeng Liao
 
Deep Learning Hardware: Past, Present, & Future
Deep Learning Hardware: Past, Present, & FutureDeep Learning Hardware: Past, Present, & Future
Deep Learning Hardware: Past, Present, & FutureRouyun Pan
 
Deep neural networks
Deep neural networksDeep neural networks
Deep neural networksSi Haem
 
Convolutional neural networks
Convolutional neural networksConvolutional neural networks
Convolutional neural networksSlobodan Blazeski
 
Ai ml dl_bct and mariners-1
Ai  ml dl_bct and mariners-1Ai  ml dl_bct and mariners-1
Ai ml dl_bct and mariners-1cmmindia2017
 
Neural Networks and Deep Learning
Neural Networks and Deep LearningNeural Networks and Deep Learning
Neural Networks and Deep LearningAsim Jalis
 

La actualidad más candente (20)

Deep learning - what is it and why now?
Deep learning - what is it and why now?Deep learning - what is it and why now?
Deep learning - what is it and why now?
 
Intro to Deep Learning for Computer Vision
Intro to Deep Learning for Computer VisionIntro to Deep Learning for Computer Vision
Intro to Deep Learning for Computer Vision
 
101: Convolutional Neural Networks
101: Convolutional Neural Networks 101: Convolutional Neural Networks
101: Convolutional Neural Networks
 
deeplearning
deeplearningdeeplearning
deeplearning
 
Deep learning - Conceptual understanding and applications
Deep learning - Conceptual understanding and applicationsDeep learning - Conceptual understanding and applications
Deep learning - Conceptual understanding and applications
 
From neural networks to deep learning
From neural networks to deep learningFrom neural networks to deep learning
From neural networks to deep learning
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
 
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
 
Top 10 deep learning algorithms you should know in
Top 10 deep learning algorithms you should know inTop 10 deep learning algorithms you should know in
Top 10 deep learning algorithms you should know in
 
Three classes of deep learning networks
Three classes of deep learning networksThree classes of deep learning networks
Three classes of deep learning networks
 
Building distributed deep learning engine
Building distributed deep learning engineBuilding distributed deep learning engine
Building distributed deep learning engine
 
Deep learning
Deep learning Deep learning
Deep learning
 
Deep Learning Hardware: Past, Present, & Future
Deep Learning Hardware: Past, Present, & FutureDeep Learning Hardware: Past, Present, & Future
Deep Learning Hardware: Past, Present, & Future
 
Tutorial on Deep Learning
Tutorial on Deep LearningTutorial on Deep Learning
Tutorial on Deep Learning
 
Deep neural networks
Deep neural networksDeep neural networks
Deep neural networks
 
Deep learning
Deep learning Deep learning
Deep learning
 
Convolutional neural networks
Convolutional neural networksConvolutional neural networks
Convolutional neural networks
 
deep learning
deep learningdeep learning
deep learning
 
Ai ml dl_bct and mariners-1
Ai  ml dl_bct and mariners-1Ai  ml dl_bct and mariners-1
Ai ml dl_bct and mariners-1
 
Neural Networks and Deep Learning
Neural Networks and Deep LearningNeural Networks and Deep Learning
Neural Networks and Deep Learning
 

Similar a Looking into the Black Box - A Theoretical Insight into Deep Learning Networks

Deep Learning - The Past, Present and Future of Artificial Intelligence
Deep Learning - The Past, Present and Future of Artificial IntelligenceDeep Learning - The Past, Present and Future of Artificial Intelligence
Deep Learning - The Past, Present and Future of Artificial IntelligenceLukas Masuch
 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual IntroductionLukas Masuch
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learningAmr Rashed
 
Big Data Intelligence: from Correlation Discovery to Causal Reasoning
Big Data Intelligence: from Correlation Discovery to Causal Reasoning Big Data Intelligence: from Correlation Discovery to Causal Reasoning
Big Data Intelligence: from Correlation Discovery to Causal Reasoning Wanjin Yu
 
Deep learning fundamentals workshop
Deep learning fundamentals workshopDeep learning fundamentals workshop
Deep learning fundamentals workshopSatnam Singh
 
Introduction to ANN Principles and its Applications in Solar Energy Technology
Introduction to ANN Principles and its Applications in Solar Energy TechnologyIntroduction to ANN Principles and its Applications in Solar Energy Technology
Introduction to ANN Principles and its Applications in Solar Energy TechnologyAli Al-Waeli
 
BASIC CONCEPT OF DEEP LEARNING.pptx
BASIC CONCEPT OF DEEP LEARNING.pptxBASIC CONCEPT OF DEEP LEARNING.pptx
BASIC CONCEPT OF DEEP LEARNING.pptxRiteshPandey184067
 
Synthetic dialogue generation with Deep Learning
Synthetic dialogue generation with Deep LearningSynthetic dialogue generation with Deep Learning
Synthetic dialogue generation with Deep LearningS N
 
Deep learning Techniques JNTU R20 UNIT 2
Deep learning Techniques JNTU R20 UNIT 2Deep learning Techniques JNTU R20 UNIT 2
Deep learning Techniques JNTU R20 UNIT 2EXAMCELLH4
 
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...ijscai
 
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...ijscai
 
Unsupervised learning models of invariant features in images: Recent developm...
Unsupervised learning models of invariant features in images: Recent developm...Unsupervised learning models of invariant features in images: Recent developm...
Unsupervised learning models of invariant features in images: Recent developm...IJSCAI Journal
 
let's dive to deep learning
let's dive to deep learninglet's dive to deep learning
let's dive to deep learningMohamed Essam
 

Similar a Looking into the Black Box - A Theoretical Insight into Deep Learning Networks (20)

Deep Learning - The Past, Present and Future of Artificial Intelligence
Deep Learning - The Past, Present and Future of Artificial IntelligenceDeep Learning - The Past, Present and Future of Artificial Intelligence
Deep Learning - The Past, Present and Future of Artificial Intelligence
 
Cnn
CnnCnn
Cnn
 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual Introduction
 
AINL 2016: Filchenkov
AINL 2016: FilchenkovAINL 2016: Filchenkov
AINL 2016: Filchenkov
 
Machine Learning
Machine LearningMachine Learning
Machine Learning
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Big Data Intelligence: from Correlation Discovery to Causal Reasoning
Big Data Intelligence: from Correlation Discovery to Causal Reasoning Big Data Intelligence: from Correlation Discovery to Causal Reasoning
Big Data Intelligence: from Correlation Discovery to Causal Reasoning
 
Deep learning fundamentals workshop
Deep learning fundamentals workshopDeep learning fundamentals workshop
Deep learning fundamentals workshop
 
Introduction to ANN Principles and its Applications in Solar Energy Technology
Introduction to ANN Principles and its Applications in Solar Energy TechnologyIntroduction to ANN Principles and its Applications in Solar Energy Technology
Introduction to ANN Principles and its Applications in Solar Energy Technology
 
BASIC CONCEPT OF DEEP LEARNING.pptx
BASIC CONCEPT OF DEEP LEARNING.pptxBASIC CONCEPT OF DEEP LEARNING.pptx
BASIC CONCEPT OF DEEP LEARNING.pptx
 
Novi sad ai event 1-2018
Novi sad ai event 1-2018Novi sad ai event 1-2018
Novi sad ai event 1-2018
 
DEEP LEARNING.docx
DEEP LEARNING.docxDEEP LEARNING.docx
DEEP LEARNING.docx
 
Synthetic dialogue generation with Deep Learning
Synthetic dialogue generation with Deep LearningSynthetic dialogue generation with Deep Learning
Synthetic dialogue generation with Deep Learning
 
Deep learning Techniques JNTU R20 UNIT 2
Deep learning Techniques JNTU R20 UNIT 2Deep learning Techniques JNTU R20 UNIT 2
Deep learning Techniques JNTU R20 UNIT 2
 
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
 
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
UNSUPERVISED LEARNING MODELS OF INVARIANT FEATURES IN IMAGES: RECENT DEVELOPM...
 
Unsupervised learning models of invariant features in images: Recent developm...
Unsupervised learning models of invariant features in images: Recent developm...Unsupervised learning models of invariant features in images: Recent developm...
Unsupervised learning models of invariant features in images: Recent developm...
 
let's dive to deep learning
let's dive to deep learninglet's dive to deep learning
let's dive to deep learning
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
 
Deep learning
Deep learningDeep learning
Deep learning
 

Más de Dinesh V

Data Science Deep Roots in Healthcare Industry
Data Science Deep Roots in Healthcare IndustryData Science Deep Roots in Healthcare Industry
Data Science Deep Roots in Healthcare IndustryDinesh V
 
Healthcare evolves with Data Interoperability
Healthcare evolves with Data InteroperabilityHealthcare evolves with Data Interoperability
Healthcare evolves with Data InteroperabilityDinesh V
 
Mastering Customers Moments in Retail Realm
Mastering Customers Moments in Retail Realm Mastering Customers Moments in Retail Realm
Mastering Customers Moments in Retail Realm Dinesh V
 
Human in-the-loop in Machine Learning
Human in-the-loop in Machine LearningHuman in-the-loop in Machine Learning
Human in-the-loop in Machine LearningDinesh V
 
Explainable AI
Explainable AIExplainable AI
Explainable AIDinesh V
 
Sentiment Analysis
Sentiment AnalysisSentiment Analysis
Sentiment AnalysisDinesh V
 

Más de Dinesh V (6)

Data Science Deep Roots in Healthcare Industry
Data Science Deep Roots in Healthcare IndustryData Science Deep Roots in Healthcare Industry
Data Science Deep Roots in Healthcare Industry
 
Healthcare evolves with Data Interoperability
Healthcare evolves with Data InteroperabilityHealthcare evolves with Data Interoperability
Healthcare evolves with Data Interoperability
 
Mastering Customers Moments in Retail Realm
Mastering Customers Moments in Retail Realm Mastering Customers Moments in Retail Realm
Mastering Customers Moments in Retail Realm
 
Human in-the-loop in Machine Learning
Human in-the-loop in Machine LearningHuman in-the-loop in Machine Learning
Human in-the-loop in Machine Learning
 
Explainable AI
Explainable AIExplainable AI
Explainable AI
 
Sentiment Analysis
Sentiment AnalysisSentiment Analysis
Sentiment Analysis
 

Último

Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAndrey Devyatkin
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingEdi Saputra
 
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
 
Exploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusExploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusZilliz
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDropbox
 
AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024The Digital Insurer
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProduct Anonymous
 
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Angeliki Cooney
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businesspanagenda
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024The Digital Insurer
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MIND CTI
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistandanishmna97
 
Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024The Digital Insurer
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century educationjfdjdjcjdnsjd
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesrafiqahmad00786416
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...apidays
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native ApplicationsWSO2
 

Último (20)

Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
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...
 
Exploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusExploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with Milvus
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor Presentation
 
AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistan
 
Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 

Looking into the Black Box - A Theoretical Insight into Deep Learning Networks

  • 1. Looking into the Black Box- A Theoretical Insight into Deep Learning Networks
  • 2. What is Deep Learning? Deep learning is a branch of machine learning which is based on Artificial Neural Networks. As neural networks mimics the human brain, so does the deep learning based on neural networks. Deep learning is a representation learning. The automated formation of useful representations from data. There are variety of deep learning networks such as Multilayer Perceptron (MLP), Autoencoders (AE), Convolution Neural Network (CNN), Recurrent Neural Network (RNN). 02
  • 4. 04 Why Deep Learning is Successful? Deep learning models are large and deep Artificial Neural Networks. A neural network (“NN”) can be well presented in a directed acyclic graph. The input layer takes in signal vectors; one or multiple hidden layers process the outputs of the previous layer. But why does it work now? Why deep learning is successful now than ever?
  • 5. 05 Understands the problem & check Feasibility for Deep Learning Test the model’s Performance Choose Deep Learning Algorithm Identifies Relevant Data & prepares it Training Algorithm Architecture of Deep Learning
  • 6. I I I H O H H H H H H H I - Input layer H - Hidden layer O - Output layer Deep Learning Model 06
  • 7. How do data science techniques scale with amount of data? Performance Amount of data Why Deep Learning Deep learning Older learning algorithms 07
  • 8. Why is Deep Learning Successful? The reason for Deep learning networks success is: We have a lot more data. We have much powerful computers. A large and deep neural network has many layers and many nodes in each layer, resulting in many parameters to tune. Without enough data, we cannot learn parameters efficiently. Without powerful computers, learning would be too slow and insufficient. 08
  • 9. Why is Deep Learning Successful? Neural networks are either encoders, decoders, or a combination of both: Encoders find patterns in raw data to form compact, useful representations. Decoders generate high-resolution data from those representations. The generated data is either new examples or descriptive knowledge. 09
  • 10. Traditional Pattern Recognition: Fixed/Handcrafted Feature Extractor Mainstream Pattern Recognition: Unsupervised mid-level features Deep Learning: Representations are hierarchical and trained Feature Extractor Mid-Level Features Low-Level Features Feature Extractor Trainable Classifier Trainable Classifier Trainable Classifier Mid-Level Features High-Level Features 10
  • 11. Supervised Learning Unsupervised Learning Reinforcement Learning Feed Forward Neural Networks Convolutional Neural Networks Recurrent Neural Networks Encoder-Decoder Architectures Autoencoder Generative Adversarial Networks Networks for Actions, Values, Policies, & Models Types of Deep Learning Model 11
  • 12. Feed Forward Neural Networks (FFNNs) FFNNs dating back to 1940s, are networks that don’t have any cycles. Data passes from input to output in a single pass without any “state memory”. Technically, most networks in deep learning can be considered FFNNs, but usually “FFNN” refers to its simplest variant: a densely- connected multilayer perceptron (MLP). Dense encoders are used to map an already compact set of numbers on the input to a prediction: either a classification (discrete) or a regression (continuous). 12
  • 13. Feed Forward Neural Networks A Few Numbers Dense Encoder Representation Prediction Prediction Ground TruthOutputNetworkInput 13
  • 14. Convolutional Neural Networks (CNNs) CNNs are feed forward neural networks that use a spatial-invariance trick to efficiently learn local patterns, most commonly, in images. Spatial-invariance means that a subject's ear in the top left of the image has the same features as a subject's ear in bottom right of the image. CNNs share weights across space to make the detection of subject's ears and other patterns more efficient. Instead of using only densely-connected layers, they use convolutional layers (convolutional encoder). These networks are used for image classification, object detection, video action recognition, and any data that has some spatial invariance in its structure. 14
  • 15. Convolutional Neural Networks An Image Convolutional Encoder Representation Prediction Prediction Ground TruthOutputNetworkInput 15
  • 16. Recurrent Neural Networks (RNNs) RNNs are networks that have cycles and therefore have “state memory”. They can be unrolled in time to become feed forward networks where the weights are shared. Just as CNNs share weights across “space”, RNNs share weights across “time”. This allows them to process and efficiently represent patterns in sequential data. Many variants of RNNs modules have been developed, including LSTMs and GRUs, to help learn patterns in longer sequences. Applications include natural language modeling, speech recognition, speech generation, etc. 16
  • 17. Recurrent Neural Network Sequence Recurrent Encoder Representation Prediction Prediction Ground TruthOutputNetworkInput 17
  • 18. Encoder-Decoder Architectures FFNNs, CNNs, and RNNs presented in first 3 sections are simply networks that make a prediction using either a dense encoder, convolutional encoder, or a recurrent encoder, respectively. These encoders can be combined or switched depending on the kind of raw data we’re trying to form a useful representation of. “Encoder-Decoder” architecture is a higher-level concept that builds on the encoding step to, instead of making a prediction, generate a high-dimensional output via a decoding step by upsampling the compressed representation. Applications include semantic segmentation, machine translation, etc. 18
  • 20. Autoencoders Autoencoders are one of the simpler forms of “unsupervised learning” taking the encoder-decoder architecture and learning to generate an exact copy of the input data. Since the encoded representation is much smaller than the input data, the network is forced to learn how to form the most meaningful representation. Since the ground truth data comes from the input data, no human effort is required. In other words, it’s self-supervised. Applications include unsupervised embeddings, image denoising, etc. 20
  • 21. 21 Autoencoder Exact copy of input Any Encoder Representation Ground TruthNetwork Any Decoder Network Image, Text, etc. Input
  • 22. Generative Adversarial Networks (GANs) GANs are a framework for training networks optimized for generating new realistic samples from a particular representation. In its simplest form, the training process involves two networks. One network, called the generator, generates new data instances, trying to fool the other network, the discriminator, that classifies images as real or fake. They can generate images from a particular class, the ability to map images from one domain to another, and an incredible increase in realism of generated images. 22
  • 23. Generative Adversarial Networks Real Image Generator Fake Image Ground TruthNetwork Discriminator Network Noise Input Output Prediction Real or Fake Throw away after training 23
  • 24. Deep Reinforcement Learning (Deep RL) Deep RL allows us to apply neural networks in simulated or real-world environments when sequences of decisions need to be made. When the learning is done by a neural network, we refer to it as Deep Reinforcement Learning (Deep RL). There are three types of RL frameworks: policy-based, value-based, and model-based. The distinction is what the neural network is tasked with learning. This includes game playing, robotics , neural architecture search, and much more. 24
  • 25. World State Sample Any Encoder Representation Action Output Reward Ground TruthInput Network Deep Reinforcement Learning 25
  • 26. 26 Advantages Best in-class performance on problems. Reduces need for feature engineering. Eliminates unnecessary costs. Identifies defects easily that are difficult to detect.
  • 27. 27 Applications of Deep Learning Models Automatic Text Generation – Corpus of text is learned and from this model new text is generated, word-by-word or character-by- character. Then this model can learn how to spell, punctuate, form sentences, or it may even capture the style. Healthcare – Helps in diagnosing various diseases and treating it. Automatic Machine Translation – Certain words, sentences or phrases in one language is transformed into another language (Deep Learning is achieving top results in the areas of text, images).
  • 28. 28 Applications of Deep Learning Models Image Recognition – Recognizes and identifies people and objects in images as well as to understand content and context. This area is already being used in Gaming, Retail, Tourism, etc. Predicting Earthquakes – Teaches a computer to perform viscoelastic computations which are used in predicting earthquakes.
  • 29. To assist you with our services please reach us at hello@mitosistech.com www.mitosistech.com IND: +91-7824035173 US: +1-(415) 251-2064