Deep neural networks with a set of node-wise varying activation functions

DOI10.1016/j.neunet.2020.03.004zbMath1468.68184DBLPjournals/nn/JangCKLY20arXiv1809.03721OpenAlexW3011818954WikidataQ90594532 ScholiaQ90594532MaRDI QIDQ1980402

Seungjoon Yang, Jaehong Kim, Hyunjoong Cho, Jaeyeon Lee, Jinhyeok Jang

Publication date: 8 September 2021

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1809.03721

zbMATH Keywords

principal component analysispruningdeep networkvarying activation

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Artificial neural networks and deep learning (68T07)

Uses Software

• Cohn-Kanade
• CIFAR
• ImageNet
• Adam
• ThiNet
• AlexNet

Cites Work

• Learning representations by back-propagating errors
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Deep neural networks with a set of node-wise varying activation functions