کنفرانس مهندسی برق ایران

صفحه اصلی / سی و چهارمین کنفرانس بین المللی مهندسی برق

Improving Artificial Neural Network Performance Using Hybrid Activation Function

نویسندگان :

Morteza Taheri¹ Sajad Haghzad Klidbary²

1- زنجان 2- زنجان

کلمات کلیدی :

Activation Function،Hybrid Activation Function،Neural Networks،Deep Learning.،Hybrid Activation Function،Cifar and Mnist Dataset.

چکیده :

Abstract- Choosing the optimal activation function for the training of deep neural networks has always posed a significant challenge due to its substantial impact on the network performance and training speed. Despite the impressive performance demonstrated by various nonlinear non-monotonic activation functions, such as rectified linear units, hyperbolic tangent, sigmoid, swish, mish, Smish, and Logish, only a restricted subset of these functions is commonly embraced in most applications, primarily because of inherent inconsistencies or other limitations. This research introduces a new hybrid activation functions designed to surpass other activation functions. The results from our experiments suggest that the new activation function(AF) we introduced performs well across diverse datasets. Also, These findings indicate that the activation function we developed are better suited for intricate deep-learning models. In comparison to Sigmoid, Relu and other AFs, our proposed activation function has increased accuracy on MNIST, Cifar10, Cifar100 dataset. Significantly, our purposed AF has the maximum accuracy (100%) compared to other well-known activation functions on MNIST dataset.

لیست مقالات

لیست مقالات بایگانی شده

RSF: Reinforcement learning based hybrid split and federated learning for edge computing environments

Alireza Soleimani - Negar Anabestani - Mahmoud Momtazpour

An Interactive Intelligent Gaming System for Movement Rehabilitation in Hemiparetic CP Children: A Case Study

Reza Zaker Tavallaei - Sepehr Foroughi - Ghazal Mohammadzadeh Ahmad abadi - Seyyed Ali Raeisussadat - Seyyed Sajjad Heydarnia - Zeynab Sadat Seyyedi - Hamid Reza Kobravi - Mehran Beiraghi Toosi - Narges Hashemi - Javad Akhondian

Semi-supervised Deep Reinforcement Learning in Decentralized Multi-Agent Collision Avoidance and Path Planning in a Complex Environment

Marzie Parooei - Mehdi Tale Masouleh - Ahmad Kalhor

RNN-Based Resilient Model Predictive Consensus Control for Nonlinear Multi-Agent Systems Under DoS Attacks: A Case Study in UAVs

Abdolah RoshanaeeDeh - Pariya Rezaei Chiyaneh - Iman Sharifi

A Robust Multi-Objective Framework for Distribution Network Expansion Planning Incorporating Distributed Generation Using Particle Swarm Optimization

Mohammad Mahdi Kordian Hamedani - Sana Sadeghi - Arshia Afshar - Reza Kafili

Joint User Association and UAV Location Optimization for Two-Tired Visible Light Communication Networks

Alireza Qazavi - Foroogh Sadat Tabataba - Mehdi Naderi Soorki

Diagnosis of Heart Diseases based on Processing Heart Sound using Machine Learning

Maryam Moulaverdi - Akbar Ranjbar

An Ensemble Model for Sleep Stages Classification

Sahar Hassanzadeh Mostafaei - Jafar Tanha - Amir Sharafkhaneh - Zohair Hassanzadeh Mostafaei - Mohammed Hussein Ali Al-jaf - Alireza Fakhim babaei

Design and Simulation of Modified Salisbury Spatial Filter using Genetic Algorithm for Improving Optical Image Processing

Mohammadmahdi Modabberanbeh - Hassan Kaatuzian - Amir Nader Askarpour

Extreme Modulation Index Using Time Periodic Epsilon-Near-Zero Materials

Atefeh Erfaniazad - Mohammad Memarian

بیشتر