The Effects of Precision Constraints in a Backpropagation Learning Network

被引：44

作者：

Hollis, Paul W. ^{[1
]}

Harper, John S. ^{[1
]}

Paulos, John J. ^{[1
]}

机构：

[1] North Carolina State Univ, Dept Elect & Comp Engn, Raleigh, NC 27695 USA

来源：

NEURAL COMPUTATION | 1990年 / 2卷 / 03期

关键词：

D O I：

10.1162/neco.1990.2.3.363

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 presents a study of precision constraints imposed by a hybrid chip architecture with analog neurons and digital backpropagation calculations. Conversions between the analog and digital domains and weight storage restrictions impose precision limits on both analog and digital calculations. It is shown through simulations that a learning system of this nature can be implemented in spite of limited resolution in the analog circuits and using fixed point arithmetic to implement the backpropagation algorithm.

引用

页码：363 / 373

页数：11

共 50 条

[41] Distributional Learning for Network Alignment with Global Constraints
Xu, Hui
Xiang, Liyao
Gan, Xiaoying
Fu, Luoyi
Wang, Xinbing
Zhou, Chenghu
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 2024, 18 (04)
[42] RAPID BACKPROPAGATION LEARNING ALGORITHMS
CHO, SB
KIM, JH
CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 1993, 12 (02) : 155 - 175
[43] Learning Multiagent Communication with Backpropagation
Sukhbaatar, Sainbayar
Szlam, Arthur
Fergus, Rob
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016), 2016, 29
[44] Meta-learning with backpropagation
Younger, AS
Hochreiter, S
Conwell, PR
IJCNN'01: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS, 2001, : 2001 - 2006
[45] Incremental backpropagation learning networks
Fu, LM
Hsu, HH
Principe, JC
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1996, 7 (03): : 757 - 761
[46] Unbiased Likelihood Backpropagation Learning
Sekino, Masashi
Nitta, Katsumi
NEURAL INFORMATION PROCESSING, PART I, 2008, 4984 : 446 - 455
[47] A Non-linear Mapping-based Generalized Backpropagation Network for Unsupervised Learning
J Chemom, 3 (241):
[48] The layer-wise method and the backpropagation hybrid approach to learning a feedforward neural network
Rubanov, NS
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2000, 11 (02): : 295 - 305
[49] Complex-Valued Neural Network and Complex-Valued Backpropagation Learning Algorithm
Nitta, Tohru
ADVANCES IN IMAGING AND ELECTRON PHYSICS, VOL 152, 2008, 152 : 153 - 220
[50] A non-linear mapping-based generalized backpropagation network for unsupervised learning
Jiang, JH
Wang, JH
Liang, YZ
Yu, RQ
JOURNAL OF CHEMOMETRICS, 1996, 10 (03) : 241 - 252

← 1 2 3 4 5 →