Designing Universally-Approximating Deep Neural Networks: A First-Order Optimization Approach-Reference-Cited by-同舟云学术

Designing Universally-Approximating Deep Neural Networks: A First-Order Optimization Approach

Published:2024-09 Issue:9 Volume:46 Page:6231-6246
ISSN:0162-8828
Container-title:IEEE Transactions on Pattern Analysis and Machine Intelligence
language:
Short-container-title:IEEE Trans. Pattern Anal. Mach. Intell.

Author:

Wu Zhoutong¹^ORCID,Xiao Mingqing²^ORCID,Fang Cong³^ORCID,Lin Zhouchen³^ORCID

Affiliation:

1. Center for Data Science, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China

2. National Key Lab of General AI, School of Intelligence Science and Technology, Peking University, Beijing, China

3. National Key Lab of General AI, School of Intelligence Science and Technology, Institute for Artificial Intelligence, Peking University, Beijing, China

Funder

National Key Research and Development Program of China

NSF China

PCL, China

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Link

http://xplorestaging.ieee.org/ielx7/34/10627928/10477580.pdf?arnumber=10477580

Reference85 articles.

1. ImageNet classification with deep convolutional neural networks;Krizhevsky

2. Googles neural machine translation system: Bridging the gap between human and machine translation;Wu,2016

3. Mastering the game of Go without human knowledge

4. Multilayer feedforward networks are universal approximators

5. Approximation by superpositions of a sigmoidal function

Cited by 1 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. Renormalized Connection for Scale-Preferred Object Detection in Satellite Imagery;IEEE Transactions on Geoscience and Remote Sensing;2024