SpinalNet: Deep Neural Network with Gradual Input

Overview

SpinalNet: Deep Neural Network with Gradual Input

This repository contains scripts for training different variations of the SpinalNet and its counterparts.

Abstract

Over the past few years, deep neural networks (DNNs) have garnered remarkable success in a diverse range of real-world applications. However, DNNs consider a large number of inputs and consist of a large number of parameters, resulting in high computational demand. We study the human somatosensory system and propose the SpinalNet to achieve higher accuracy with less computational resources. In a typical neural network (NN) architecture, the hidden layers receive inputs in the first layer and then transfer the intermediate outcomes to the next layer. In the proposed SpinalNet, the structure of hidden layers allocates to three sectors: 1) Input row, 2) Intermediate row, and 3) output row. The intermediate row of the SpinalNet contains a few neurons. The role of input segmentation is in enabling each hidden layer to receive a part of the inputs and outputs of the previous layer. Therefore, the number of incoming weights in a hidden layer is significantly lower than traditional DNNs. As all layers of the SpinalNet directly contributes to the output row, the vanishing gradient problem does not exist. We also investigate the SpinalNet fully-connected layer to several well-known DNN models and perform traditional learning and transfer learning. We observe significant error reductions with lower computational costs in most of the DNNs. We have also obtained the state-of-the-art (SOTA) performance for QMNIST, Kuzushiji-MNIST, EMNIST (Letters, Digits, and Balanced), STL-10, Bird225, Fruits 360, and Caltech-101 datasets. The scripts of the proposed SpinalNet are available at the following link: https://github.com/dipuk0506/SpinalNet

Packages Used

torch, torchvision, numpy, random, matplotlib, time, os, copy, math.

Scripts are independent. The user can download an individual script and run. Except for scripts of the 'Transfer Learning' folder, scripts are downloading data from PyTorch during the execution.

SOTA

KMNIST, QMNINT, EMNIST (Digits, Letters, Balanced), STL-10, Bird-225, Caltech-101,Fruits-360

Motivation

The SpinalNet tries to mimic the human somatosensory system to receive large data efficiently and to achieve better performance. (a) Half part of the human somatosensory system, presenting how our spinal cord receives sensory signals from our body. (b) Structure of the proposed SpinalNet. The proposed NN consists of the input row, the intermediate row, and the output row. The intermediate row contains multiple hidden layers. Each hidden layer receives a portion of the input. All layers except the first layer also receive outputs of the previous layer. The output layer adds the weighted outputs of all hidden neurons of the intermediate row. The user can also construct and train a SpinalNet for any arbitrary number of inputs, intermediate neurons, and outputs.

Universal Approximation

  • Single hidden layer NN of large width is a universal approximator.

  • If we can prove that, SpinalNet of a large depth can be equivalent to the single hidden layer NN of large width, the universal approximation is proved.

Following figure presents the visual proof of the universal approximation theorem for the proposed SpinalNet. A simplified version of SpinalNet in (a) can act as a NN of a single hidden layer, drawn in (b). Similarly, a 4 layer SpinalNet in (d)can be equal to a NN of one hidden layer (HL), containing four neurons, shown in (c).

Traditional hidden layer to Spinal Hidden Layer

Any traditional hidden layer can be converted to a spinal hidden layer. The traditional hidden layer in (a) is converted to a spinal hidden layer in (b). A spinal hidden layer has the structure of the proposed SpinalNet.

Results

Regression

Classification

Detailed classification results are available in the paper. Link to the paper: https://arxiv.org/abs/2007.03347

Simulation results on Kaggle:

[1] https://www.kaggle.com/dipuk0506/spinalnet-tl-pytorch-bird225-99-5

[2] https://www.kaggle.com/dipuk0506/spinalnet-cifar10-97-5-accuracy

[3] https://www.kaggle.com/dipuk0506/spinalnet-fruit360-99-99-accuracy

Owner
H M Dipu Kabir
H M Dipu Kabir
Honours project, on creating a depth estimation map from two stereo images of featureless regions

image-processing This module generates depth maps for shape-blocked-out images Install If working with anaconda, then from the root directory: conda e

2 Oct 17, 2022
A module for solving and visualizing Schrödinger equation.

qmsolve This is an attempt at making a solid, easy to use solver, capable of solving and visualize the Schrödinger equation for multiple particles, an

506 Dec 28, 2022
Hand-distance-measurement-game - Hand Distance Measurement Game

Hand Distance Measurement Game This is program is made to calculate the distance

Priyansh 2 Jan 12, 2022
Applying CLIP to Point Cloud Recognition.

PointCLIP: Point Cloud Understanding by CLIP This repository is an official implementation of the paper 'PointCLIP: Point Cloud Understanding by CLIP'

Renrui Zhang 175 Dec 24, 2022
Implementation for Learning to Track with Object Permanence

Learning to Track with Object Permanence A video-based MOT approach capable of tracking through full occlusions: Learning to Track with Object Permane

Toyota Research Institute - Machine Learning 91 Jan 03, 2023
Earthquake detection via fiber optic cables using deep learning

Earthquake detection via fiber optic cables using deep learning Author: Fantine Huot Getting started Update the submodules After cloning the repositor

Fantine 4 Nov 30, 2022
Script that attempts to force M1 macs into RGB mode when used with monitors that are defaulting to YPbPr.

fix_m1_rgb Script that attempts to force M1 macs into RGB mode when used with monitors that are defaulting to YPbPr. No warranty provided for using th

Kevin Gao 116 Jan 01, 2023
Transferable Unrestricted Attacks, which won 1st place in CVPR’21 Security AI Challenger: Unrestricted Adversarial Attacks on ImageNet.

Transferable Unrestricted Adversarial Examples This is the PyTorch implementation of the Arxiv paper: Towards Transferable Unrestricted Adversarial Ex

equation 16 Dec 29, 2022
Vision-Language Pre-training for Image Captioning and Question Answering

VLP This repo hosts the source code for our AAAI2020 work Vision-Language Pre-training (VLP). We have released the pre-trained model on Conceptual Cap

Luowei Zhou 373 Jan 03, 2023
The easiest tool for extracting radiomics features and training ML models on them.

Simple pipeline for experimenting with radiomics features Installation git clone https://github.com/piotrekwoznicki/ClassyRadiomics.git cd classrad pi

Piotr Woźnicki 17 Aug 04, 2022
Official codebase for "B-Pref: Benchmarking Preference-BasedReinforcement Learning" contains scripts to reproduce experiments.

B-Pref Official codebase for B-Pref: Benchmarking Preference-BasedReinforcement Learning contains scripts to reproduce experiments. Install conda env

48 Dec 20, 2022
A Fast and Stable GAN for Small and High Resolution Imagesets - pytorch

A Fast and Stable GAN for Small and High Resolution Imagesets - pytorch The official pytorch implementation of the paper "Towards Faster and Stabilize

Bingchen Liu 455 Jan 08, 2023
Official implementation of the ICCV 2021 paper: "The Power of Points for Modeling Humans in Clothing".

The Power of Points for Modeling Humans in Clothing (ICCV 2021) This repository contains the official PyTorch implementation of the ICCV 2021 paper: T

Qianli Ma 158 Nov 24, 2022
Official implementation of "Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision" ECCV2020

XDVioDet Official implementation of "Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision" ECCV2020. The proj

peng 64 Dec 12, 2022
FastReID is a research platform that implements state-of-the-art re-identification algorithms.

FastReID is a research platform that implements state-of-the-art re-identification algorithms.

JDAI-CV 2.8k Jan 07, 2023
Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch

Rotary Embeddings - Pytorch A standalone library for adding rotary embeddings to transformers in Pytorch, following its success as relative positional

Phil Wang 110 Dec 30, 2022
Pytorch implementation of PCT: Point Cloud Transformer

PCT: Point Cloud Transformer This is a Pytorch implementation of PCT: Point Cloud Transformer.

Yi_Zhang 265 Dec 22, 2022
🙄 Difficult algorithm, Simple code.

🎉TensorFlow2.0-Examples🎉! "Talk is cheap, show me the code." ----- Linus Torvalds Created by YunYang1994 This tutorial was designed for easily divin

1.7k Dec 25, 2022
PyTorch implementation of paper “Unbiased Scene Graph Generation from Biased Training”

A new codebase for popular Scene Graph Generation methods (2020). Visualization & Scene Graph Extraction on custom images/datasets are provided. It's also a PyTorch implementation of paper “Unbiased

Kaihua Tang 824 Jan 03, 2023
In this project we combine techniques from neural voice cloning and musical instrument synthesis to achieve good results from as little as 16 seconds of target data.

Neural Instrument Cloning In this project we combine techniques from neural voice cloning and musical instrument synthesis to achieve good results fro

Erland 127 Dec 23, 2022