Deep and Shallow Architecture of Multilayer Neural Networks

被引：59

作者：

Chang, Chih-Hung ^{[1
]}

机构：

[1] Natl Univ Kaohsiung, Dept Appl Math, Kaohsiung 81148, Taiwan

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS | 2015年 / 26卷 / 10期

关键词：

Deep architecture; factor-like matrix; multilayer neural networks (MNNs); sofic shift; topological entropy; PATTERN-FORMATION; ALGORITHM;

D O I：

10.1109/TNNLS.2014.2387439

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper focuses on the deep and shallow architecture of multilayer neural networks (MNNs). The demonstration of whether or not an MNN can be replaced by another MNN with fewer layers is equivalent to studying the topological conjugacy of its hidden layers. This paper provides a systematic methodology to indicate when two hidden spaces are topologically conjugated. Furthermore, some criteria are presented for some specific cases.

引用

页码：2477 / 2486

页数：10

共 50 条

[1] Shallow2Deep: Restraining Neural Networks Opacity Through Neural Architecture Search
Agiollo, Andrea
Ciatto, Giovanni
Omicini, Andrea
EXPLAINABLE AND TRANSPARENT AI AND MULTI-AGENT SYSTEMS, EXTRAAMAS 2021, 2021, 12688 : 63 - 82
[2] Explaining Neural Networks - Deep and Shallow
Hammer, Barbara
ADVANCES IN SELF-ORGANIZING MAPS, LEARNING VECTOR QUANTIZATION, INTERPRETABLE MACHINE LEARNING, AND BEYOND, WSOM PLUS 2024, 2024, 1087 : 139 - 140
[3] Improving Deep Neural Networks with Multilayer Maxout Networks
Sun, Weichen
Su, Fei
Wang, Leiquan
2014 IEEE VISUAL COMMUNICATIONS AND IMAGE PROCESSING CONFERENCE, 2014, : 334 - 337
[4] Shallow Neural Networks to Deep Neural Networks for Probabilistic Wind Forecasting
Arora, Parul
Panigrahi, B. K.
Suganthan, P. N.
2021 IEEE INTERNATIONAL CONFERENCE ON COMPUTING, COMMUNICATION, AND INTELLIGENT SYSTEMS (ICCCIS), 2021, : 377 - 382
[5] Limitations on approximation by deep and shallow neural networks
Petrova, Guergana
Wojtaszczyk, Przemyslaw
JOURNAL OF MACHINE LEARNING RESEARCH, 2023, 24
[6] Architecture Disentanglement for Deep Neural Networks
Hu, Jie
Cao, Liujuan
Tong, Tong
Ye, Qixiang
Zhang, Shengchuan
Li, Ke
Huang, Feiyue
Shao, Ling
Ji, Rongrong
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 652 - 661
[7] The Mixture of Neural Networks Adapted to Multilayer Feedforward Architecture
Torres-Sospedra, Joaquin
Hernandez-Espinosa, Carlos
Fernandez-Redondo, Mercedes
INTELLIGENT COMPUTING, PART I: INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING, ICIC 2006, PART I, 2006, 4113 : 488 - 493
[8] An Efficient Hardware Architecture for Multilayer Spiking Neural Networks
Luo, Yuling
Wan, Lei
Liu, Junxiu
Zhang, Jinlei
Cao, Yi
NEURAL INFORMATION PROCESSING (ICONIP 2017), PT VI, 2017, 10639 : 786 - 795
[9] Architecture of neural processing unit for deep neural networks
Lee, Kyuho J.
HARDWARE ACCELERATOR SYSTEMS FOR ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING, 2021, 122 : 217 - 245
[10] The Impact of Architecture on the Deep Neural Networks Training
Rozycki, Pawel
Kolbusz, Janusz
Malinowski, Aleksander
Wilamowski, Bogdan
2019 12TH INTERNATIONAL CONFERENCE ON HUMAN SYSTEM INTERACTION (HSI), 2019, : 41 - 46

← 1 2 3 4 5 →