An approach combining a new weight initialization method and constructive algorithm to configure a single Feedforward Neural Network for multi-class classification-Reference-Cited by-同舟云学术

An approach combining a new weight initialization method and constructive algorithm to configure a single Feedforward Neural Network for multi-class classification

Published:2021-11 Issue: Volume:106 Page:104495
ISSN:0952-1976
Container-title:Engineering Applications of Artificial Intelligence
language:en
Short-container-title:Engineering Applications of Artificial Intelligence

Author:

Fontes Cristiano Hora^ORCID,Embiruçu Marcelo

Publisher

Elsevier BV

Subject

Electrical and Electronic Engineering,Artificial Intelligence,Control and Systems Engineering

Reference37 articles.

1. Solving the linear interval tolerance problem for weight initialization of neural networks;Adam;Neural Netw.,2014

2. Neural Networks and Deep Learning;Aggarwal,2018

3. Pruning algorithms of neural networks - a comparative study review;Augasta;Cent. Eur. J. Comput. Sci.,2003

4. UCI Machine Learning Repository;Bache,2013

5. Artificial Intelligence in Cancer: Diagnostic to Tailored Treatment;Belciug,2020

Cited by 11 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. Dynamic multilayer growth: Parallel vs. sequential approaches;PLOS ONE;2024-05-09

2. Machine learning-aided damage identification of mock-up spent nuclear fuel assemblies in a sealed dry storage canister;Engineering Applications of Artificial Intelligence;2024-02

3. Nonlinear and infinite gain scheduling neural predictive control of the outlet temperature in a parabolic trough solar field: A comparative study;Engineering Applications of Artificial Intelligence;2023-11

4. Cluster analysis of carboniferous gas reservoirs and application of recovery prediction model;Frontiers in Earth Science;2023-06-12

5. Training Feedforward Neural Networks Using an Enhanced Marine Predators Algorithm;Processes;2023-03-17