Deep Neural Network with Adaptive Parametric Rectified Linear Units and its Fast Learning
-
Published:2022-03-30
Issue:
Volume:
Page:11-18
-
ISSN:2312-5381
-
Container-title:International Journal of Computing
-
language:
-
Short-container-title:IJC
Author:
Bodyanskiy Yevgeniy,Deineko Anastasiia,Skorik Viktoria,Brodetskyi Filip
Abstract
The adaptive parametric rectified linear unit (AdPReLU) as an activation function of the deep neural network is proposed in the article. The main benefit of the proposed system is adjusted activation function whose parameters are tuning parallel with synaptic weights in online mode. The algorithm of the simultaneous learning of all neurons parameters with AdPReLU and the modified backpropagation procedure based on this algorithm is introduced. The approach under consideration permits to reduce volume of the training data set and increase tuning speed of the DNN with AdPReLU. The proposed approach could be applied in the deep convolutional neural networks (CNN) in conditions of the small value of training data sets and additional requirements for system performance. The main feature of DNN under consideration is possibility to tune not only synaptic weights but the parameters of activation function too. The effectiveness of this approach is proved by experimental modeling.
Publisher
Research Institute for Intelligent Computer Systems
Subject
Computer Networks and Communications,Hardware and Architecture,Information Systems,Software,Computer Science (miscellaneous)
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Comparative DNN-Based Classification of Customers Feedbacks in E-Commerce Platform;2023 IEEE 12th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS);2023-09-07
2. Unsupervised Pre-Training of Deep Neural Classifiers;2023 IEEE 12th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS);2023-09-07