SlideShare una empresa de Scribd logo
1 de 21
Problems with CNNs and Introduction to Capsule
Neural Networks
Vipul Vaibhaw
Talk Overview
● Why Neural Networks?
● Introduction to Convolutional Neural Networks
● The Problems with Convolutional Neural Networks
● Introduction to Capsule Neural Networks
Why Neural Networks?
1. Different approach than conventional algorithmic approach
2. Great for identifying patterns.
3. More generalized solutions.
4. Neural networks and conventional algorithmic computers are not in
competition but complement each other.
Convolutional Neural Networks
In machine learning, a convolutional
neural network (CNN, or ConvNet) is a
class of deep, feed-forward artificial
neural networks that has successfully
been applied to analyzing visual
imagery.
Applications
1. Image recognition
2. Video Analysis
3. Natural language processing
4. Checkers
5. Go
many more...
Demo
Video Summarization using Deep Semantics Features
Research Paper - https://arxiv.org/abs/1609.08758
The Problems with ConvNets
Let’s look at the architecture
Anybody can implement ConvNets
Cannot extrapolate understanding of Geometry!
SEVEN ??
No Relationship b/w nose and mouth!
Sub-sampling/Pooling of the images loses the relationship between higher
level parts such as Nose and Mouth.
These spatial relationship are very much needed for identity recognition
This is not a face!
Equivariance v/s Invariance
● Pooling is invariant to small changes in viewpoints.
● Equivariance - Changes in viewpoints leads to corresponding changes in
Neural Networks.
Fooling Deep Neural Nets!
● Deep neural networks(DNN) is not continuous and very sensitive to tiny
perturbation on the input vectors.
● CNN perform poorly when there is Noise in the image.
● Say, changing 1 pixel in an image won’t have any effect on a picture of Cat
to a human being but when this attack was carried on a DNN its
confidence dropped from 98.7% to 73.8%
Link to the research paper - https://arxiv.org/abs/1710.08864
Capsule Neural Networks!
Capsule Neural Networks
What is a capsule?
● A capsule is a group of neurons whose activity vector represents the
instantiation parameters of a specific type of entity such as an object or
object part.
● It nests a new layer inside a layer.
● Instead of making a layer deeper in height, it makes a layer deeper in a
structure.
More about Capsules
● Capsules are like cortical columns in human brains.
● Capsules are supposed to produce equivariant features, like a 3D graphic
model: given the model with just a simple transformation we can derive
all its poses
Dynamic Routing in Capsule NN
Research paper published by Hinton - https://arxiv.org/abs/1710.09829v1
The cost of this new architecture?
● The data flow is more complicated
● No idea how stable it will be for attacking difficult learning problems.
● That makes it harder to calculate gradients, and the model may suffer
more from vanishing gradients.
● Scalability?
Conclusion
● ConvNets is proven to solve many real world problems but it has its own
drawbacks.
● Capsule Nets are a promising development to ConvNets.
● It is too early to predict the success of Capsule Nets because it is yet to be
implemented on datasets other than MNIST dataset.
Thank You!
● Email - vaibhaw.vipul@gmail.com
● Github - https://github.com/vaibhawvipul

Más contenido relacionado

La actualidad más candente

(Research Note) Delving deeper into convolutional neural networks for camera ...
(Research Note) Delving deeper into convolutional neural networks for camera ...(Research Note) Delving deeper into convolutional neural networks for camera ...
(Research Note) Delving deeper into convolutional neural networks for camera ...
Jacky Liu
 
proposal_pura
proposal_puraproposal_pura
proposal_pura
Erick Lin
 
Soft Computing-173101
Soft Computing-173101Soft Computing-173101
Soft Computing-173101
AMIT KUMAR
 
SCALING THE HTM SPATIAL POOLER
SCALING THE HTM SPATIAL POOLERSCALING THE HTM SPATIAL POOLER
SCALING THE HTM SPATIAL POOLER
ijaia
 

La actualidad más candente (19)

Matrix capsules with em routing
Matrix capsules with em routingMatrix capsules with em routing
Matrix capsules with em routing
 
Unsupervised Object Detection
Unsupervised Object DetectionUnsupervised Object Detection
Unsupervised Object Detection
 
(Research Note) Delving deeper into convolutional neural networks for camera ...
(Research Note) Delving deeper into convolutional neural networks for camera ...(Research Note) Delving deeper into convolutional neural networks for camera ...
(Research Note) Delving deeper into convolutional neural networks for camera ...
 
[DL輪読会]Learning Visible Connectivity Dynamics for Cloth Smoothing (CoRL2021)
[DL輪読会]Learning Visible Connectivity Dynamics for Cloth Smoothing (CoRL2021)[DL輪読会]Learning Visible Connectivity Dynamics for Cloth Smoothing (CoRL2021)
[DL輪読会]Learning Visible Connectivity Dynamics for Cloth Smoothing (CoRL2021)
 
Distance-based bias in model-directed optimization of additively decomposable...
Distance-based bias in model-directed optimization of additively decomposable...Distance-based bias in model-directed optimization of additively decomposable...
Distance-based bias in model-directed optimization of additively decomposable...
 
proposal_pura
proposal_puraproposal_pura
proposal_pura
 
Associative Memory Model について
Associative Memory Model についてAssociative Memory Model について
Associative Memory Model について
 
세미나 20170929
세미나 20170929세미나 20170929
세미나 20170929
 
Convolutional Neural Networks for Sentence Classification
Convolutional Neural Networks for Sentence ClassificationConvolutional Neural Networks for Sentence Classification
Convolutional Neural Networks for Sentence Classification
 
PRML 5.5.6-5.6
PRML 5.5.6-5.6PRML 5.5.6-5.6
PRML 5.5.6-5.6
 
Towards Dropout Training for Convolutional Neural Networks
Towards Dropout Training for Convolutional Neural Networks Towards Dropout Training for Convolutional Neural Networks
Towards Dropout Training for Convolutional Neural Networks
 
A SURVEY OF SPIKING NEURAL NETWORKS AND SUPPORT VECTOR MACHINE PERFORMANCE BY...
A SURVEY OF SPIKING NEURAL NETWORKS AND SUPPORT VECTOR MACHINE PERFORMANCE BY...A SURVEY OF SPIKING NEURAL NETWORKS AND SUPPORT VECTOR MACHINE PERFORMANCE BY...
A SURVEY OF SPIKING NEURAL NETWORKS AND SUPPORT VECTOR MACHINE PERFORMANCE BY...
 
Pixel Recurrent Neural Networks
Pixel Recurrent Neural NetworksPixel Recurrent Neural Networks
Pixel Recurrent Neural Networks
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
 
[PR12] PixelRNN- Jaejun Yoo
[PR12] PixelRNN- Jaejun Yoo[PR12] PixelRNN- Jaejun Yoo
[PR12] PixelRNN- Jaejun Yoo
 
Soft Computing-173101
Soft Computing-173101Soft Computing-173101
Soft Computing-173101
 
SCALING THE HTM SPATIAL POOLER
SCALING THE HTM SPATIAL POOLERSCALING THE HTM SPATIAL POOLER
SCALING THE HTM SPATIAL POOLER
 
On the High Dimentional Information Processing in Quaternionic Domain and its...
On the High Dimentional Information Processing in Quaternionic Domain and its...On the High Dimentional Information Processing in Quaternionic Domain and its...
On the High Dimentional Information Processing in Quaternionic Domain and its...
 
Conditional Image Generation with PixelCNN Decoders
Conditional Image Generation with PixelCNN DecodersConditional Image Generation with PixelCNN Decoders
Conditional Image Generation with PixelCNN Decoders
 

Similar a Problems with CNNs and Introduction to capsule neural networks

A SYSTEMATIC STUDY OF DEEP LEARNING ARCHITECTURES FOR ANALYSIS OF GLAUCOMA AN...
A SYSTEMATIC STUDY OF DEEP LEARNING ARCHITECTURES FOR ANALYSIS OF GLAUCOMA AN...A SYSTEMATIC STUDY OF DEEP LEARNING ARCHITECTURES FOR ANALYSIS OF GLAUCOMA AN...
A SYSTEMATIC STUDY OF DEEP LEARNING ARCHITECTURES FOR ANALYSIS OF GLAUCOMA AN...
ijaia
 

Similar a Problems with CNNs and Introduction to capsule neural networks (20)

[PR12] Inception and Xception - Jaejun Yoo
[PR12] Inception and Xception - Jaejun Yoo[PR12] Inception and Xception - Jaejun Yoo
[PR12] Inception and Xception - Jaejun Yoo
 
IRJET-Breast Cancer Detection using Convolution Neural Network
IRJET-Breast Cancer Detection using Convolution Neural NetworkIRJET-Breast Cancer Detection using Convolution Neural Network
IRJET-Breast Cancer Detection using Convolution Neural Network
 
A SYSTEMATIC STUDY OF DEEP LEARNING ARCHITECTURES FOR ANALYSIS OF GLAUCOMA AN...
A SYSTEMATIC STUDY OF DEEP LEARNING ARCHITECTURES FOR ANALYSIS OF GLAUCOMA AN...A SYSTEMATIC STUDY OF DEEP LEARNING ARCHITECTURES FOR ANALYSIS OF GLAUCOMA AN...
A SYSTEMATIC STUDY OF DEEP LEARNING ARCHITECTURES FOR ANALYSIS OF GLAUCOMA AN...
 
Towards better analysis of deep convolutional neural networks
Towards better analysis of deep convolutional neural networksTowards better analysis of deep convolutional neural networks
Towards better analysis of deep convolutional neural networks
 
Artificial neural networks(AI UNIT 3)
Artificial neural networks(AI UNIT 3)Artificial neural networks(AI UNIT 3)
Artificial neural networks(AI UNIT 3)
 
[PR12] understanding deep learning requires rethinking generalization
[PR12] understanding deep learning requires rethinking generalization[PR12] understanding deep learning requires rethinking generalization
[PR12] understanding deep learning requires rethinking generalization
 
Deep Learning With Neural Networks
Deep Learning With Neural NetworksDeep Learning With Neural Networks
Deep Learning With Neural Networks
 
Deep Learning Training at Intel
Deep Learning Training at IntelDeep Learning Training at Intel
Deep Learning Training at Intel
 
BASIC CONCEPT OF DEEP LEARNING.pptx
BASIC CONCEPT OF DEEP LEARNING.pptxBASIC CONCEPT OF DEEP LEARNING.pptx
BASIC CONCEPT OF DEEP LEARNING.pptx
 
Image captioning
Image captioningImage captioning
Image captioning
 
CNN.pptx.pdf
CNN.pptx.pdfCNN.pptx.pdf
CNN.pptx.pdf
 
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdf
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdfCCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdf
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdf
 
fundamentals-of-neural-networks-laurene-fausett
fundamentals-of-neural-networks-laurene-fausettfundamentals-of-neural-networks-laurene-fausett
fundamentals-of-neural-networks-laurene-fausett
 
Rupesh-ibPRIA final
Rupesh-ibPRIA finalRupesh-ibPRIA final
Rupesh-ibPRIA final
 
101: Convolutional Neural Networks
101: Convolutional Neural Networks 101: Convolutional Neural Networks
101: Convolutional Neural Networks
 
Recent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectivesRecent advances of AI for medical imaging : Engineering perspectives
Recent advances of AI for medical imaging : Engineering perspectives
 
Evolving Comprehensible Neural Network Trees
Evolving Comprehensible Neural Network TreesEvolving Comprehensible Neural Network Trees
Evolving Comprehensible Neural Network Trees
 
Learning where to look: focus and attention in deep vision
Learning where to look: focus and attention in deep visionLearning where to look: focus and attention in deep vision
Learning where to look: focus and attention in deep vision
 
Quantum neural network
Quantum neural networkQuantum neural network
Quantum neural network
 
Image Captioning Generator using Deep Machine Learning
Image Captioning Generator using Deep Machine LearningImage Captioning Generator using Deep Machine Learning
Image Captioning Generator using Deep Machine Learning
 

Último

AI Mastery 201: Elevating Your Workflow with Advanced LLM Techniques
AI Mastery 201: Elevating Your Workflow with Advanced LLM TechniquesAI Mastery 201: Elevating Your Workflow with Advanced LLM Techniques
AI Mastery 201: Elevating Your Workflow with Advanced LLM Techniques
VictorSzoltysek
 
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
Health
 
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
TECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providerTECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service provider
mohitmore19
 
introduction-to-automotive Andoid os-csimmonds-ndctechtown-2021.pdf
introduction-to-automotive Andoid os-csimmonds-ndctechtown-2021.pdfintroduction-to-automotive Andoid os-csimmonds-ndctechtown-2021.pdf
introduction-to-automotive Andoid os-csimmonds-ndctechtown-2021.pdf
VishalKumarJha10
 

Último (20)

AI Mastery 201: Elevating Your Workflow with Advanced LLM Techniques
AI Mastery 201: Elevating Your Workflow with Advanced LLM TechniquesAI Mastery 201: Elevating Your Workflow with Advanced LLM Techniques
AI Mastery 201: Elevating Your Workflow with Advanced LLM Techniques
 
8257 interfacing 2 in microprocessor for btech students
8257 interfacing 2 in microprocessor for btech students8257 interfacing 2 in microprocessor for btech students
8257 interfacing 2 in microprocessor for btech students
 
Diamond Application Development Crafting Solutions with Precision
Diamond Application Development Crafting Solutions with PrecisionDiamond Application Development Crafting Solutions with Precision
Diamond Application Development Crafting Solutions with Precision
 
The Ultimate Test Automation Guide_ Best Practices and Tips.pdf
The Ultimate Test Automation Guide_ Best Practices and Tips.pdfThe Ultimate Test Automation Guide_ Best Practices and Tips.pdf
The Ultimate Test Automation Guide_ Best Practices and Tips.pdf
 
How To Use Server-Side Rendering with Nuxt.js
How To Use Server-Side Rendering with Nuxt.jsHow To Use Server-Side Rendering with Nuxt.js
How To Use Server-Side Rendering with Nuxt.js
 
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
 
VTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learnVTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learn
 
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
 
Software Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsSoftware Quality Assurance Interview Questions
Software Quality Assurance Interview Questions
 
Exploring the Best Video Editing App.pdf
Exploring the Best Video Editing App.pdfExploring the Best Video Editing App.pdf
Exploring the Best Video Editing App.pdf
 
TECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providerTECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service provider
 
introduction-to-automotive Andoid os-csimmonds-ndctechtown-2021.pdf
introduction-to-automotive Andoid os-csimmonds-ndctechtown-2021.pdfintroduction-to-automotive Andoid os-csimmonds-ndctechtown-2021.pdf
introduction-to-automotive Andoid os-csimmonds-ndctechtown-2021.pdf
 
Introducing Microsoft’s new Enterprise Work Management (EWM) Solution
Introducing Microsoft’s new Enterprise Work Management (EWM) SolutionIntroducing Microsoft’s new Enterprise Work Management (EWM) Solution
Introducing Microsoft’s new Enterprise Work Management (EWM) Solution
 
Azure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdf
Azure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdfAzure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdf
Azure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdf
 
How To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected WorkerHow To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected Worker
 
Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...
Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...
Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...
 
Direct Style Effect Systems - The Print[A] Example - A Comprehension Aid
Direct Style Effect Systems -The Print[A] Example- A Comprehension AidDirect Style Effect Systems -The Print[A] Example- A Comprehension Aid
Direct Style Effect Systems - The Print[A] Example - A Comprehension Aid
 
Define the academic and professional writing..pdf
Define the academic and professional writing..pdfDefine the academic and professional writing..pdf
Define the academic and professional writing..pdf
 
How to Choose the Right Laravel Development Partner in New York City_compress...
How to Choose the Right Laravel Development Partner in New York City_compress...How to Choose the Right Laravel Development Partner in New York City_compress...
How to Choose the Right Laravel Development Partner in New York City_compress...
 
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
 

Problems with CNNs and Introduction to capsule neural networks

  • 1. Problems with CNNs and Introduction to Capsule Neural Networks Vipul Vaibhaw
  • 2. Talk Overview ● Why Neural Networks? ● Introduction to Convolutional Neural Networks ● The Problems with Convolutional Neural Networks ● Introduction to Capsule Neural Networks
  • 3. Why Neural Networks? 1. Different approach than conventional algorithmic approach 2. Great for identifying patterns. 3. More generalized solutions. 4. Neural networks and conventional algorithmic computers are not in competition but complement each other.
  • 4. Convolutional Neural Networks In machine learning, a convolutional neural network (CNN, or ConvNet) is a class of deep, feed-forward artificial neural networks that has successfully been applied to analyzing visual imagery.
  • 5. Applications 1. Image recognition 2. Video Analysis 3. Natural language processing 4. Checkers 5. Go many more...
  • 6. Demo Video Summarization using Deep Semantics Features Research Paper - https://arxiv.org/abs/1609.08758
  • 7. The Problems with ConvNets
  • 8. Let’s look at the architecture
  • 10. Cannot extrapolate understanding of Geometry! SEVEN ??
  • 11. No Relationship b/w nose and mouth! Sub-sampling/Pooling of the images loses the relationship between higher level parts such as Nose and Mouth. These spatial relationship are very much needed for identity recognition This is not a face!
  • 12. Equivariance v/s Invariance ● Pooling is invariant to small changes in viewpoints. ● Equivariance - Changes in viewpoints leads to corresponding changes in Neural Networks.
  • 13. Fooling Deep Neural Nets! ● Deep neural networks(DNN) is not continuous and very sensitive to tiny perturbation on the input vectors. ● CNN perform poorly when there is Noise in the image. ● Say, changing 1 pixel in an image won’t have any effect on a picture of Cat to a human being but when this attack was carried on a DNN its confidence dropped from 98.7% to 73.8% Link to the research paper - https://arxiv.org/abs/1710.08864
  • 16. What is a capsule? ● A capsule is a group of neurons whose activity vector represents the instantiation parameters of a specific type of entity such as an object or object part. ● It nests a new layer inside a layer. ● Instead of making a layer deeper in height, it makes a layer deeper in a structure.
  • 17. More about Capsules ● Capsules are like cortical columns in human brains. ● Capsules are supposed to produce equivariant features, like a 3D graphic model: given the model with just a simple transformation we can derive all its poses
  • 18. Dynamic Routing in Capsule NN Research paper published by Hinton - https://arxiv.org/abs/1710.09829v1
  • 19. The cost of this new architecture? ● The data flow is more complicated ● No idea how stable it will be for attacking difficult learning problems. ● That makes it harder to calculate gradients, and the model may suffer more from vanishing gradients. ● Scalability?
  • 20. Conclusion ● ConvNets is proven to solve many real world problems but it has its own drawbacks. ● Capsule Nets are a promising development to ConvNets. ● It is too early to predict the success of Capsule Nets because it is yet to be implemented on datasets other than MNIST dataset.
  • 21. Thank You! ● Email - vaibhaw.vipul@gmail.com ● Github - https://github.com/vaibhawvipul

Notas del editor

  1. It is just a quick introduction to Neural Networks. 2. For the last ten years Neural networks have attracted a great deal of attention. They offer an alternative approach to computing and to understanding of the human brain. This approach is not something new. The first artificial neuron was produced in 1943 by the neurophysiologist Warren McCulloch and the logician Walter Pits. During the sixties, for reasons that are out of the scope of this article, people turned away from neural networks and concentrated in the symbolic side of Artificial Intelligence. Only in the eighties scientists saw the real potential of neural networks.
  2. After this slide, show a demo of video summarization.
  3. AlexNET
  4. Geoffery Hinton