• Home
  • Search
  • Activation function cyclically switchable convolutional neural network model.
  • https://doi.org/10.7717/peerj-cs.2756Copy DOI Icon

Activation function cyclically switchable convolutional neural network model.

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Neural networks are a state-of-the-art approach that performs well for many tasks. The activation function (AF) is an important hyperparameter that creates an output against the coming inputs to the neural network model. AF significantly affects the training and performance of the neural network model. Therefore, selecting the most optimal AF for processing input data in neural networks is important. Determining the optimal AF is often a difficult task. To overcome this difficulty, studies on trainable AFs have been carried out in the literature in recent years. This study presents a different approach apart from fixed or trainable AF approaches. For this purpose, the activation function cyclically switchable convolutional neural network (AFCS-CNN) model structure is proposed. The AFCS-CNN model structure does not use a fixed AF value during training. It is designed in a self-regulating model structure by switching the AF during model training. The proposed model structure is based on the logic of starting training with the most optimal AF selection among many AFs and cyclically selecting the next most optimal AF depending on the performance decrease during neural network training. Any convolutional neural network (CNN) model can be easily used in the proposed model structure. In this way, a simple but effective perspective has been presented. In this study, first, ablation studies have been carried out using the Cifar-10 dataset to determine the CNN models to be used in the AFCS-CNN model structure and the specific hyperparameters of the proposed model structure. After the models and hyperparameters were determined, expansion experiments were carried out using different datasets with the proposed model structure. The results showed that the AFCS-CNN model structure achieved state-of-the-art success in many CNN models and different datasets.

Similar Papers
  • PDF
  • Research Article
  • Citations314

The Influence of the Activation Function in a Convolution Neural Network Model of Facial Expression Recognition

  • Mar 10, 2020
  • Applied Sciences
  • Yingying Wang +3
  • Book Chapter
  • Citations16

Text Sentiment Analysis Based on Convolutional Neural Network and Bidirectional LSTM Model

  • Jan 01, 2018
  • Mengjiao Song +3
  • Research Article

К ВОПРОСУ АВТОМАТИЗАЦИИ РАЗМЕТКИ ДАННЫХ ДЛЯ ОБУЧЕНИЯ НЕЙРОННЫХ СЕТЕЙ, ИСПОЛЬЗУЕМЫХ В ЖИВОТНОВОДСТВЕ

  • Jan 01, 2024
  • Elektrotekhnologii i elektrooborudovanie v APK
  • Oksana Lipa +4
  • Research Article
  • Citations52

Exploring the Potential of VGG-16 Architecture for Accurate Brain Tumor Detection Using Deep Learning

  • Jun 06, 2023
  • Journal of Computers, Mechanical and Management
  • Prerepa Gayathri +4
  • PDF
  • Research Article
  • Citations7

Application of Convolution Neural Network (CNN) Model Combined with Pyramid Algorithm in Aerobics Action Recognition

  • Jan 01, 2021
  • Computational Intelligence and Neuroscience
  • Qi Liang
  • Conference Article
  • Citations1

Analyzing the effect of hyperparameters in a automobile classifier based on convolutional neural networks

  • Oct 01, 2016
  • Elian Laura Riveros +2
  • PDF
  • Research Article
  • Citations13

Study on Driver Cross-Subject Emotion Recognition Based on Raw Multi-Channels EEG Data

  • May 23, 2023
  • Electronics
  • Zhirong Wang +2
  • PDF
  • Research Article
  • Citations5

Identification of Epileptogenic and Non-epileptogenic High-Frequency Oscillations Using a Multi-Feature Convolutional Neural Network Model.

  • Oct 15, 2021
  • Frontiers in Neurology
  • Guoping Ren +10
  • Research Article
  • Citations1

A systematic approach for segmenting voiced/unvoiced signals using fuzzy-logic system and general fusion of neural network models for phonemes-based speech recognition

  • Jan 01, 2020
  • Journal of Intelligent & Fuzzy Systems
  • Sathees Kumar Nataraj +3
  • Research Article

Long-term prediction of heart failure using an ECG-based fine-tuned self-supervised neural network model identifies 23 genetic loci implicating electrophysiological mechanisms

  • Nov 01, 2025
  • European Heart Journal
  • E Caballero +5
  • PDF
  • Research Article
  • Citations41

Credit Risk Prediction Model for Listed Companies Based on CNN-LSTM and Attention Mechanism

  • Mar 30, 2023
  • Electronics
  • Jingyuan Li +3
  • Conference Article
  • Citations6

A deep neural network for information extraction from web pages

  • Sep 01, 2017
  • S Nagarajan +1
  • Research Article
  • Citations16

Convolutional neural network-based wind pressure prediction on low-rise buildings

  • May 01, 2024
  • Engineering Structures
  • Youqin Huang +4
  • Research Article
  • Citations17

A multiscale neural network model for the prediction on the equivalent permeability of discrete fracture network

  • Nov 07, 2022
  • Journal of Petroleum Science and Engineering
  • Chenhong Zhu +3
  • Supplementary Content
  • Citations9

Feature Extraction of Ancient Chinese Characters Based on Deep Convolution Neural Network and Big Data Analysis.

  • Jan 01, 2021
  • Computational Intelligence and Neuroscience
  • Cheng Zhang +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.