SlideShare a Scribd company logo
1 of 20
GNR638: Course Project
Kervolutional Neural Networks
Nov 21, 2021
Sahasra Ranjan Paarth Jain Atul Verma
190050102 190050076 19B090004
Tirthankar Adhikari Shrey Gupta
190070003 190100112
Introduction
➢ Convolutional neural networks
(CNNs) have been tremendously
successful in computer vision, e.g.
image recognition and object
detection
➢ But convolutions are not able to
express non-linear behaviour, they
can do so using an activation
function but even though it can only
provide pointwise non-linearity.
Hence, the paper used kervolution
which uses the kernel trick to solve
this.
Recent Approaches to the Problem
A minimal character based CNN architecture based model:
https://arxiv.org/ftp/arxiv/papers/1901/1901.06032.pdf
https://www.analyticsvidhya.com/blog/2020/10/what-is-the-
convolutional-neural-network-architecture/
Our Implementation to the Problem
● We used Kervolutional layers to deploy our model using PyTorch.
● When Kernel type is linear, it’s a usual CNN, but in our implementation we
changed our Kernel types across Polynomial and Gaussian to introduce non-
linearity which in turn, gave better performance.
Dataset and Features
MNIST CIFAR10
Baseline Model: Kervolution
● The ith element of the
convolution output f(x) is
calculated as a simple inner
product between vector x(i) and
vector w.
● Whereas the kervolution is
calculated via the kernel trick
which essentially maps the
vector in a non linear space
and then takes the inner
product
Convolution
Kervolution
● Kernel function takes kervolution to non-linear space, thus
the model capacity is increased without introducing extra
parameters.
● Kervolution measures the similarity by match kernels, which
are equivalent to extracting specific features.
● One of the advantages of kervolution is that the non-linear
properties can be customized without explicit calculation.
Models Capacity and features
Polynomial Kervolution
● To show the behavior of polynomial Kervolution, the learned filters of
LeNet-5 trained for MNIST are visualized i which contains all six channels
of the first Kervolutional layer using polynomial kernel (dp = 3, cp = 1)
Continued..
● For a comparison, the learned filters from CNN are also presented. It is
interesting that some of the learned filters of KNN and CNN are quite
similar, This verifies our understanding of polynomial kernel, which is a
combination of linear and higher order terms.
● This also indicates that polynomial kervolution introduces higher order
feature interaction in a more flexible and direct way than the existing
methods.
Gaussian Kervolution
The Gaussian RBF kernel extends kervolution to infinite dimensions.
where γg (γg ∈ R+) is a hyperparameter to control the smoothness of
decision boundary.
Continued...
It extends kervolution to infinite dimensions because of the ith-degree terms in
Results
MNIST Dataset
● Test Accuracy (trained for 5 epochs):
● Convolution : 98.1%
● Poly-linear-linear : 98.4%
● Linear-poly-linear : 98.47%
Graph to show faster training with kervolution
●
Other Results:
Conclusions & Future Work
● Kervolution generalise convolution to non-linear space.
● Extends convolutional neural networks to kervolutional Neural
network.
● Not only retains the advantages of convolution( sharing weights and
equivalence to translation) but also enhances model capacity and
captures higher order interactions of features, via patch-wise kernel
functions without introducing additional parameters.
Future Work: Continued...
● With careful kernel chosen, the performance of CNN can be
significantly improved on MNIST, CIFAR, and ImageNet dataset
via replacing convolutional layers by kervolutional layers.
● Due to the large number of choices of kervolution, we cannot
perform a brute force search for all the possibilities.
● We expect the introduction of kervolutional layers in more
architectures and extensive hyperparameter searches can further
improve the performance.
Individual Contribution & Code
Sahasra Ranjan
(190050102)
Worked on the Kervolution Neural Networks and implemented the
training procedure on GPU using pytorch.
Paarth Jain (190050076) Worked on the training procedure and generated results for
various hyperparameters and network settings
Atul Verma (19B090004) Prepared presentation and project report
Tirthankar Adhikari
(190070003)
Debugging the implemented code and preparing presentation
Shrey Gupta (190100112)
Github Repository Link for Final code, Readme Files and Results:
GitHub Repo: https://github.com/Lhisoka/GNR-638-Project
Project PPT: https://docs.google.com/presentation/d/1-
VgwYgyPi4UW1CoTHDgVi7EISm5AbeZPVu62bCwqDsg/edit?usp=sharing
Note: All of our code is based on the following documentation:
https://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Kervolutiona
l_Neural_Networks_CVPR_2019_paper.pdf
Given the recent rapid development in this field, there
are a lot more remaining to be explored
Thank You!

More Related Content

Similar to GNR638_Course Project for spring semester

Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)Universitat Politècnica de Catalunya
 
Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)DonghyunKang12
 
物件偵測與辨識技術
物件偵測與辨識技術物件偵測與辨識技術
物件偵測與辨識技術CHENHuiMei
 
A Generalization of Transformer Networks to Graphs.pptx
A Generalization of Transformer Networks to Graphs.pptxA Generalization of Transformer Networks to Graphs.pptx
A Generalization of Transformer Networks to Graphs.pptxssuser2624f71
 
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_ReportSaptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_ReportSitakanta Mishra
 
FINAL_Team_4.pptx
FINAL_Team_4.pptxFINAL_Team_4.pptx
FINAL_Team_4.pptxnitin571047
 
Introduction to Chainer
Introduction to ChainerIntroduction to Chainer
Introduction to ChainerShunta Saito
 
Autoencoders for image_classification
Autoencoders for image_classificationAutoencoders for image_classification
Autoencoders for image_classificationCenk Bircanoğlu
 
Quantum transfer learning for image classification
Quantum transfer learning for image classificationQuantum transfer learning for image classification
Quantum transfer learning for image classificationTELKOMNIKA JOURNAL
 
Neural Architecture Search: Learning How to Learn
Neural Architecture Search: Learning How to LearnNeural Architecture Search: Learning How to Learn
Neural Architecture Search: Learning How to LearnKwanghee Choi
 
intro-to-cnn-April_2020.pptx
intro-to-cnn-April_2020.pptxintro-to-cnn-April_2020.pptx
intro-to-cnn-April_2020.pptxssuser3aa461
 
DLD meetup 2017, Efficient Deep Learning
DLD meetup 2017, Efficient Deep LearningDLD meetup 2017, Efficient Deep Learning
DLD meetup 2017, Efficient Deep LearningBrodmann17
 
Hyper-parameter optimization of convolutional neural network based on particl...
Hyper-parameter optimization of convolutional neural network based on particl...Hyper-parameter optimization of convolutional neural network based on particl...
Hyper-parameter optimization of convolutional neural network based on particl...journalBEEI
 
Machine learning project
Machine learning projectMachine learning project
Machine learning projectHarsh Jain
 
Handwritten Digit Recognition(Convolutional Neural Network) PPT
Handwritten Digit Recognition(Convolutional Neural Network) PPTHandwritten Digit Recognition(Convolutional Neural Network) PPT
Handwritten Digit Recognition(Convolutional Neural Network) PPTRishabhTyagi48
 

Similar to GNR638_Course Project for spring semester (20)

CNN.pptx.pdf
CNN.pptx.pdfCNN.pptx.pdf
CNN.pptx.pdf
 
Mnist report
Mnist reportMnist report
Mnist report
 
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)
 
Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)
 
物件偵測與辨識技術
物件偵測與辨識技術物件偵測與辨識技術
物件偵測與辨識技術
 
A Generalization of Transformer Networks to Graphs.pptx
A Generalization of Transformer Networks to Graphs.pptxA Generalization of Transformer Networks to Graphs.pptx
A Generalization of Transformer Networks to Graphs.pptx
 
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_ReportSaptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
 
Mnist report ppt
Mnist report pptMnist report ppt
Mnist report ppt
 
FINAL_Team_4.pptx
FINAL_Team_4.pptxFINAL_Team_4.pptx
FINAL_Team_4.pptx
 
Sp19_P2.pptx
Sp19_P2.pptxSp19_P2.pptx
Sp19_P2.pptx
 
Introduction to Chainer
Introduction to ChainerIntroduction to Chainer
Introduction to Chainer
 
Introduction to Chainer
Introduction to ChainerIntroduction to Chainer
Introduction to Chainer
 
Autoencoders for image_classification
Autoencoders for image_classificationAutoencoders for image_classification
Autoencoders for image_classification
 
Quantum transfer learning for image classification
Quantum transfer learning for image classificationQuantum transfer learning for image classification
Quantum transfer learning for image classification
 
Neural Architecture Search: Learning How to Learn
Neural Architecture Search: Learning How to LearnNeural Architecture Search: Learning How to Learn
Neural Architecture Search: Learning How to Learn
 
intro-to-cnn-April_2020.pptx
intro-to-cnn-April_2020.pptxintro-to-cnn-April_2020.pptx
intro-to-cnn-April_2020.pptx
 
DLD meetup 2017, Efficient Deep Learning
DLD meetup 2017, Efficient Deep LearningDLD meetup 2017, Efficient Deep Learning
DLD meetup 2017, Efficient Deep Learning
 
Hyper-parameter optimization of convolutional neural network based on particl...
Hyper-parameter optimization of convolutional neural network based on particl...Hyper-parameter optimization of convolutional neural network based on particl...
Hyper-parameter optimization of convolutional neural network based on particl...
 
Machine learning project
Machine learning projectMachine learning project
Machine learning project
 
Handwritten Digit Recognition(Convolutional Neural Network) PPT
Handwritten Digit Recognition(Convolutional Neural Network) PPTHandwritten Digit Recognition(Convolutional Neural Network) PPT
Handwritten Digit Recognition(Convolutional Neural Network) PPT
 

Recently uploaded

Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur EscortsCall Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur EscortsCall Girls in Nagpur High Profile
 
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130Suhani Kapoor
 
AKTU Computer Networks notes --- Unit 3.pdf
AKTU Computer Networks notes ---  Unit 3.pdfAKTU Computer Networks notes ---  Unit 3.pdf
AKTU Computer Networks notes --- Unit 3.pdfankushspencer015
 
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Christo Ananth
 
Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)simmis5
 
Introduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptxIntroduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptxupamatechverse
 
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINEMANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINESIVASHANKAR N
 
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLSMANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLSSIVASHANKAR N
 
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls in Nagpur High Profile
 
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
UNIT-III FMM. DIMENSIONAL ANALYSIS
UNIT-III FMM.        DIMENSIONAL ANALYSISUNIT-III FMM.        DIMENSIONAL ANALYSIS
UNIT-III FMM. DIMENSIONAL ANALYSISrknatarajan
 
UNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular ConduitsUNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular Conduitsrknatarajan
 
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...roncy bisnoi
 
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escortsranjana rawat
 
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escortsranjana rawat
 
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...ranjana rawat
 
HARDNESS, FRACTURE TOUGHNESS AND STRENGTH OF CERAMICS
HARDNESS, FRACTURE TOUGHNESS AND STRENGTH OF CERAMICSHARDNESS, FRACTURE TOUGHNESS AND STRENGTH OF CERAMICS
HARDNESS, FRACTURE TOUGHNESS AND STRENGTH OF CERAMICSRajkumarAkumalla
 

Recently uploaded (20)

Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur EscortsCall Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
 
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
VIP Call Girls Service Kondapur Hyderabad Call +91-8250192130
 
AKTU Computer Networks notes --- Unit 3.pdf
AKTU Computer Networks notes ---  Unit 3.pdfAKTU Computer Networks notes ---  Unit 3.pdf
AKTU Computer Networks notes --- Unit 3.pdf
 
Roadmap to Membership of RICS - Pathways and Routes
Roadmap to Membership of RICS - Pathways and RoutesRoadmap to Membership of RICS - Pathways and Routes
Roadmap to Membership of RICS - Pathways and Routes
 
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
 
Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)
 
Introduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptxIntroduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptx
 
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINEMANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
MANUFACTURING PROCESS-II UNIT-2 LATHE MACHINE
 
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLSMANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
 
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
 
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
UNIT-III FMM. DIMENSIONAL ANALYSIS
UNIT-III FMM.        DIMENSIONAL ANALYSISUNIT-III FMM.        DIMENSIONAL ANALYSIS
UNIT-III FMM. DIMENSIONAL ANALYSIS
 
UNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular ConduitsUNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular Conduits
 
Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024
 
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
 
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
 
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
 
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
 
HARDNESS, FRACTURE TOUGHNESS AND STRENGTH OF CERAMICS
HARDNESS, FRACTURE TOUGHNESS AND STRENGTH OF CERAMICSHARDNESS, FRACTURE TOUGHNESS AND STRENGTH OF CERAMICS
HARDNESS, FRACTURE TOUGHNESS AND STRENGTH OF CERAMICS
 

GNR638_Course Project for spring semester

  • 1. GNR638: Course Project Kervolutional Neural Networks Nov 21, 2021 Sahasra Ranjan Paarth Jain Atul Verma 190050102 190050076 19B090004 Tirthankar Adhikari Shrey Gupta 190070003 190100112
  • 2. Introduction ➢ Convolutional neural networks (CNNs) have been tremendously successful in computer vision, e.g. image recognition and object detection ➢ But convolutions are not able to express non-linear behaviour, they can do so using an activation function but even though it can only provide pointwise non-linearity. Hence, the paper used kervolution which uses the kernel trick to solve this.
  • 3. Recent Approaches to the Problem A minimal character based CNN architecture based model: https://arxiv.org/ftp/arxiv/papers/1901/1901.06032.pdf https://www.analyticsvidhya.com/blog/2020/10/what-is-the- convolutional-neural-network-architecture/
  • 4. Our Implementation to the Problem ● We used Kervolutional layers to deploy our model using PyTorch. ● When Kernel type is linear, it’s a usual CNN, but in our implementation we changed our Kernel types across Polynomial and Gaussian to introduce non- linearity which in turn, gave better performance.
  • 6. Baseline Model: Kervolution ● The ith element of the convolution output f(x) is calculated as a simple inner product between vector x(i) and vector w. ● Whereas the kervolution is calculated via the kernel trick which essentially maps the vector in a non linear space and then takes the inner product Convolution Kervolution
  • 7. ● Kernel function takes kervolution to non-linear space, thus the model capacity is increased without introducing extra parameters. ● Kervolution measures the similarity by match kernels, which are equivalent to extracting specific features. ● One of the advantages of kervolution is that the non-linear properties can be customized without explicit calculation. Models Capacity and features
  • 8. Polynomial Kervolution ● To show the behavior of polynomial Kervolution, the learned filters of LeNet-5 trained for MNIST are visualized i which contains all six channels of the first Kervolutional layer using polynomial kernel (dp = 3, cp = 1)
  • 9. Continued.. ● For a comparison, the learned filters from CNN are also presented. It is interesting that some of the learned filters of KNN and CNN are quite similar, This verifies our understanding of polynomial kernel, which is a combination of linear and higher order terms. ● This also indicates that polynomial kervolution introduces higher order feature interaction in a more flexible and direct way than the existing methods.
  • 10. Gaussian Kervolution The Gaussian RBF kernel extends kervolution to infinite dimensions. where γg (γg ∈ R+) is a hyperparameter to control the smoothness of decision boundary.
  • 11. Continued... It extends kervolution to infinite dimensions because of the ith-degree terms in
  • 12. Results MNIST Dataset ● Test Accuracy (trained for 5 epochs): ● Convolution : 98.1% ● Poly-linear-linear : 98.4% ● Linear-poly-linear : 98.47%
  • 13. Graph to show faster training with kervolution
  • 15. Conclusions & Future Work ● Kervolution generalise convolution to non-linear space. ● Extends convolutional neural networks to kervolutional Neural network. ● Not only retains the advantages of convolution( sharing weights and equivalence to translation) but also enhances model capacity and captures higher order interactions of features, via patch-wise kernel functions without introducing additional parameters.
  • 16. Future Work: Continued... ● With careful kernel chosen, the performance of CNN can be significantly improved on MNIST, CIFAR, and ImageNet dataset via replacing convolutional layers by kervolutional layers. ● Due to the large number of choices of kervolution, we cannot perform a brute force search for all the possibilities. ● We expect the introduction of kervolutional layers in more architectures and extensive hyperparameter searches can further improve the performance.
  • 17. Individual Contribution & Code Sahasra Ranjan (190050102) Worked on the Kervolution Neural Networks and implemented the training procedure on GPU using pytorch. Paarth Jain (190050076) Worked on the training procedure and generated results for various hyperparameters and network settings Atul Verma (19B090004) Prepared presentation and project report Tirthankar Adhikari (190070003) Debugging the implemented code and preparing presentation Shrey Gupta (190100112)
  • 18. Github Repository Link for Final code, Readme Files and Results: GitHub Repo: https://github.com/Lhisoka/GNR-638-Project Project PPT: https://docs.google.com/presentation/d/1- VgwYgyPi4UW1CoTHDgVi7EISm5AbeZPVu62bCwqDsg/edit?usp=sharing Note: All of our code is based on the following documentation: https://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Kervolutiona l_Neural_Networks_CVPR_2019_paper.pdf
  • 19. Given the recent rapid development in this field, there are a lot more remaining to be explored