IRO Journals

Journal of Ubiquitous Computing and Communication Technologies

Comparison of Stock Price Prediction Models using Pre-trained Neural Networks
Volume-3 | Issue-2

Efficient Two Stage Identification for Face mask detection using Multiclass Deep Learning Approach
Volume-3 | Issue-2

Design an Adaptive Hybrid Approach for Genetic Algorithm to Detect Effective Malware Detection in Android Division
Volume-3 | Issue-2

Blockchain Framework for Communication between Vehicle through IoT Devices and Sensors
Volume-3 | Issue-2

Gas Leakage Detection in Pipeline by SVM classifier with Automatic Eddy Current based Defect Recognition Method
Volume-3 | Issue-3

A Review on Data Securing Techniques using Internet of Medical Things
Volume-3 | Issue-3

Machine Learning Algorithms Performance Analysis for VLSI IC Design
Volume-3 | Issue-2

Maximizing the Prediction Accuracy in Tweet Sentiment Extraction using Tensor Flow based Deep Neural Networks
Volume-3 | Issue-2

Assimilation of IoT sensors for Data Visualization in a Smart Campus Environment
Volume-3 | Issue-4

DDOS ATTACK DETECTION IN TELECOMMUNICATION NETWORK USING MACHINE LEARNING
Volume-1 | Issue-1

Gas Leakage Detection in Pipeline by SVM classifier with Automatic Eddy Current based Defect Recognition Method
Volume-3 | Issue-3

Design an Adaptive Hybrid Approach for Genetic Algorithm to Detect Effective Malware Detection in Android Division
Volume-3 | Issue-2

Comparison of Stock Price Prediction Models using Pre-trained Neural Networks
Volume-3 | Issue-2

Construction of a Framework for Selecting an Effective Learning Procedure in the School-Level Sector of Online Teaching Informatics
Volume-3 | Issue-4

Machine Learning Algorithms Performance Analysis for VLSI IC Design
Volume-3 | Issue-2

Efficient Two Stage Identification for Face mask detection using Multiclass Deep Learning Approach
Volume-3 | Issue-2

Characterizing WDT subsystem of a Wi-Fi controller in an Automobile based on MIPS32 CPU platform across PVT
Volume-2 | Issue-4

Assimilation of IoT sensors for Data Visualization in a Smart Campus Environment
Volume-3 | Issue-4

Design of Data Mining Techniques for Online Blood Bank Management by CNN Model
Volume-3 | Issue-3

Ethereum and IOTA based Battery Management System with Internet of Vehicles
Volume-3 | Issue-3

Home / Archives / Volume-3 / Issue-1 / Article-2

Volume - 3 | Issue - 1 | march 2021

Overview of Configuring Adaptive Activation Functions for Deep Neural Networks - A Comparative Study
Pages: 10-22
Published
01 May, 2021
Abstract

Recently, the deep neural networks (DNN) have demonstrated many performances in the pattern recognition paradigm. The research studies on DNN include depth layer networks, filters, training and testing datasets. Deep neural network is providing many solutions for nonlinear partial differential equations (PDE). This research article comprises of many activation functions for each neuron. Besides, these activation networks are allowing many neurons within the neuron networks. In this network, the multitude of the functions will be selected between node by node to minimize the classification error. This is the reason for selecting the adaptive activation function for deep neural networks. Therefore, the activation functions are adapted with every neuron on the network, which is used to reduce the classification error during the process. This research article discusses the scaling factor for activation function that provides better optimization for the process in the dynamic changes of procedure. The proposed adaptive activation function has better learning capability than fixed activation function in any neural network. The research articles compare the convergence rate, early training function, and accuracy between existing methods. Besides, this research work provides improvements in debt ideas of the learning process of various neural networks. This learning process works and tests the solution available in the domain of various frequency bands. In addition to that, both forward and inverse problems of the parameters in the overriding equation will be identified. The proposed method is very simple architecture and efficiency, robustness, and accuracy will be high when considering the nonlinear function. The overall classification performance will be improved in the resulting networks, which have been trained with common datasets. The proposed work is compared with the recent findings in neuroscience research and proved better performance.

Keywords

Deep networks Adaptive activation function

Full Article PDF Download Article PDF 
×

Currently, subscription is the only source of revenue. The subscription resource covers the operating expenses such as web presence, online version, pre-press preparations, and staff wages.

To access the full PDF, please complete the payment process.

Subscription Details

Category Fee
Article Access Charge
For single article (Indian)
1,200 INR
Article Access Charge
For single article (non-Indian)
15 USD
Open Access Fee (Indian) 5,000 INR
Open Access Fee (non-Indian) 80 USD
Annual Subscription Fee
For 1 Journal (Indian)
15,000 INR
Annual Subscription Fee
For 1 Journal (non-Indian)
200 USD
secure PAY INR / USD
Subscription form: click here