Optimizing Performance of Feedforward and Convolutional Neural Networks through Dynamic Activation Functions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rane, Chinmay, Tyagi, Kanishka, Manry, Michael
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917592444174336
author Rane, Chinmay
Tyagi, Kanishka
Manry, Michael
author_facet Rane, Chinmay
Tyagi, Kanishka
Manry, Michael
contents Deep learning training training algorithms are a huge success in recent years in many fields including speech, text,image video etc. Deeper and deeper layers are proposed with huge success with resnet structures having around 152 layers. Shallow convolution neural networks(CNN's) are still an active research, where some phenomena are still unexplained. Activation functions used in the network are of utmost importance, as they provide non linearity to the networks. Relu's are the most commonly used activation function.We show a complex piece-wise linear(PWL) activation in the hidden layer. We show that these PWL activations work much better than relu activations in our networks for convolution neural networks and multilayer perceptrons. Result comparison in PyTorch for shallow and deep CNNs are given to further strengthen our case.
format Preprint
id arxiv_https___arxiv_org_abs_2308_05724
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Optimizing Performance of Feedforward and Convolutional Neural Networks through Dynamic Activation Functions
Rane, Chinmay
Tyagi, Kanishka
Manry, Michael
Machine Learning
Computational Engineering, Finance, and Science
Neural and Evolutionary Computing
Deep learning training training algorithms are a huge success in recent years in many fields including speech, text,image video etc. Deeper and deeper layers are proposed with huge success with resnet structures having around 152 layers. Shallow convolution neural networks(CNN's) are still an active research, where some phenomena are still unexplained. Activation functions used in the network are of utmost importance, as they provide non linearity to the networks. Relu's are the most commonly used activation function.We show a complex piece-wise linear(PWL) activation in the hidden layer. We show that these PWL activations work much better than relu activations in our networks for convolution neural networks and multilayer perceptrons. Result comparison in PyTorch for shallow and deep CNNs are given to further strengthen our case.
title Optimizing Performance of Feedforward and Convolutional Neural Networks through Dynamic Activation Functions
topic Machine Learning
Computational Engineering, Finance, and Science
Neural and Evolutionary Computing
url https://arxiv.org/abs/2308.05724