Understanding Convolutional Neural Networks from Theoretical Perspective via Volterra Convolution

Overview

nnvolterra

Run Code

Compile first: make compile

Run all codes: make all

Test xconv: make npxconv_test

MNIST dataset needs to be downloaded, converted to numpy format, and placed to mnist/ folder.

Train MNIST network: make mnist_train

Test MNIST network: make mnist_try

Hack MNIST network: make mnist_hack

Required

  • python
  • numpy
  • pytorch
  • g++ 9.3.0
  • xelatex [optional]: for mnist_draw.py

About Files

  • xconvlibrary
    • xconvolution.hpp: core lib
    • npxconv.cpp: cpp to python
    • npxconv.py: interface for python
    • npxconv_setup.py: setup
    • npxconv_test.py: test file
  • outer convolution
    • oconv_draw.py: nnfragile and three example images of outer convolution
    • oconv_rank.py: compute rank for outer convolution and neural network to Volterra Convolution
    • oconv_rank_draw.py: draw images from oconv_rank.py
  • mnist hack
    • mnist_module.py: the module
    • mnist_train.py: train this module in training set
    • mnist_try.py: check module in test set
    • mnist_hack.py: try to hack the module
    • mnist_draw.py: slightly draw the hack result
  • other
    • tensordec.py: about tensor decomposition
    • shape_check.py: check shapes

Please Cite

@misc{li2021understanding,
      title={Understanding Convolutional Neural Networks from Theoretical Perspective via Volterra Convolution}, 
      author={Tenghui Li and Guoxu Zhou and Yuning Qiu and Qibin Zhao},
      year={2021},
      eprint={2110.09902},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}
You might also like...
Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution
Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution

FAU Implementation of the paper: Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution. Yingruo

An implementation of Video Frame Interpolation via Adaptive Separable Convolution using PyTorch
An implementation of Video Frame Interpolation via Adaptive Separable Convolution using PyTorch

This work has now been superseded by: https://github.com/sniklaus/revisiting-sepconv sepconv-slomo This is a reference implementation of Video Frame I

Improving Convolutional Networks via Attention Transfer (ICLR 2017)
Improving Convolutional Networks via Attention Transfer (ICLR 2017)

Attention Transfer PyTorch code for "Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Tran

[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator
[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator

involution Official implementation of a neural operator as described in Involution: Inverting the Inherence of Convolution for Visual Recognition (CVP

 Tensorflow Implementation for
Tensorflow Implementation for "Pre-trained Deep Convolution Neural Network Model With Attention for Speech Emotion Recognition"

Tensorflow Implementation for "Pre-trained Deep Convolution Neural Network Model With Attention for Speech Emotion Recognition" Pre-trained Deep Convo

The VarCNN is an Convolution Neural Network based approach to automate Video Assistant Referee in football.
Complex-Valued Neural Networks (CVNN)Complex-Valued Neural Networks (CVNN)

Complex-Valued Neural Networks (CVNN) Done by @NEGU93 - J. Agustin Barrachina Using this library, the only difference with a Tensorflow code is that y

Code for our ICASSP 2021 paper: SA-Net: Shuffle Attention for Deep Convolutional Neural Networks
Code for our ICASSP 2021 paper: SA-Net: Shuffle Attention for Deep Convolutional Neural Networks

SA-Net: Shuffle Attention for Deep Convolutional Neural Networks (paper) By Qing-Long Zhang and Yu-Bin Yang [State Key Laboratory for Novel Software T

《Truly shift-invariant convolutional neural networks》(2021)

Truly shift-invariant convolutional neural networks [Paper] Authors: Anadi Chaman and Ivan Dokmanić Convolutional neural networks were always assumed

Owner
null
This repository implements and evaluates convolutional networks on the Möbius strip as toy model instantiations of Coordinate Independent Convolutional Networks.

Orientation independent Möbius CNNs This repository implements and evaluates convolutional networks on the Möbius strip as toy model instantiations of

Maurice Weiler 59 Dec 9, 2022
Code for the paper A Theoretical Analysis of the Repetition Problem in Text Generation

A Theoretical Analysis of the Repetition Problem in Text Generation This repository share the code for the paper "A Theoretical Analysis of the Repeti

Zihao Fu 37 Nov 21, 2022
Propose a principled and practically effective framework for unsupervised accuracy estimation and error detection tasks with theoretical analysis and state-of-the-art performance.

Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles This project is for the paper: Detecting Errors and Estimating

Jiefeng Chen 13 Nov 21, 2022
Code to reproduce the experiments from our NeurIPS 2021 paper " The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective"

Code To run: python runner.py new --save <SAVE_NAME> --data <PATH_TO_DATA_DIR> --dataset <DATASET> --model <model_name> [options] --n 1000 - train - t

Geoff Pleiss 5 Dec 12, 2022
Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction

Welcome to Barlow Barlow is a tool for identifying the failure modes for a given neural network. To achieve this, Barlow first creates a group of imag

Sahil Singla 33 Dec 5, 2022
Does MAML Only Work via Feature Re-use? A Data Set Centric Perspective

Does-MAML-Only-Work-via-Feature-Re-use-A-Data-Set-Centric-Perspective Does MAML Only Work via Feature Re-use? A Data Set Centric Perspective Installin

null 2 Nov 7, 2022
The source code of the paper "Understanding Graph Neural Networks from Graph Signal Denoising Perspectives"

GSDN-F and GSDN-EF This repository provides a reference implementation of GSDN-F and GSDN-EF as described in the paper "Understanding Graph Neural Net

Guoji Fu 18 Nov 14, 2022
Code for Understanding Pooling in Graph Neural Networks

Select, Reduce, Connect This repository contains the code used for the experiments of: "Understanding Pooling in Graph Neural Networks" Setup Install

Daniele Grattarola 37 Dec 13, 2022
[ICLR 2021] "Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective" by Wuyang Chen, Xinyu Gong, Zhangyang Wang

Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective [PDF] Wuyang Chen, Xinyu Gong, Zhangyang Wang In ICLR 2

VITA 156 Nov 28, 2022
Code repository accompanying the paper "On Adversarial Robustness: A Neural Architecture Search perspective"

On Adversarial Robustness: A Neural Architecture Search perspective Preparation: Clone the repository: https://github.com/tdchaitanya/nas-robustness.g

Chaitanya Devaguptapu 4 Nov 10, 2022