Parallel Learning of Feedforward Neural Networks Without Error Backpropagation

被引：14

作者：

Bilski, Jaroslaw ^{[1
]}

Wilamowski, Bogdan M. ^{[2
]}

机构：

[1] Czestochowa Tech Univ, Inst Computat Intelligence, Czestochowa, Poland

[2] Auburn Univ, Auburn, AL 36849 USA

来源：

ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, ICAISC 2016 | 2016年 / 9692卷

关键词：

Forward-only computation; Neural network training; Parallel architectures; REALIZATION; ALGORITHM;

D O I：

10.1007/978-3-319-39378-0_6

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A parallel architecture of the steepest descent algorithm for training fully connected feedforward neural networks is presented. This solution is based on a new idea of learning neural networks without error backpropagation. The proposed solution is based on completely new parallel structures to effectively reduce high computational load of this algorithm. Detailed parallel 2D and 3D neural network learning structures are explicitely discussed.

引用

页码：57 / 69

页数：13

共 50 条

[41] ANALYSIS OF FEEDFORWARD-BACKPROPAGATION NEURAL NETWORKS USED IN-VEHICLE DETECTION
MANTRI, S
BULLOCK, D
[J]. TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 1995, 3 (03) : 161 - 174
[42] A Proof of a Key Formula in the Error-Backpropagation Learning Algorithm for Multiple Spiking Neural Networks
Yang, Wenyu
Yang, Dakun
Fan, Yetian
[J]. ADVANCES IN NEURAL NETWORKS - ISNN 2014, 2014, 8866 : 19 - 26
[43] Asymptotic Prediction Error Variance for Feedforward Neural Networks
Malmstrom, Magnus
Skog, Isaac
Axehill, Daniel
Gustafsson, Fredrik
[J]. IFAC PAPERSONLINE, 2020, 53 (02): : 1108 - 1113
[44] COMPARISON OF PARALLEL AND SERIAL IMPLEMENTATION OF FEEDFORWARD NEURAL NETWORKS
FOO, SK
SARATCHANDRAN, P
SUNDARARAJAN, N
[J]. JOURNAL OF MICROCOMPUTER APPLICATIONS, 1995, 18 (01): : 83 - 94
[45] A parallel algorithm for gradient training of feedforward neural networks
Hanzalek, Z
[J]. PARALLEL COMPUTING, 1998, 24 (5-6) : 823 - 839
[46] Parallel implementation of backpropagation neural networks on a heterogeneous array of transputers
Foo, SK
Saratchandran, P
Sundararajan, N
[J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 1997, 27 (01): : 118 - 126
[47] Contrastive Hebbian Feedforward Learning for Neural Networks
Kermiche, Noureddine
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (06) : 2118 - 2128
[48] Fast learning algorithms for feedforward neural networks
Jiang, MH
Gielen, G
Zhang, B
Luo, ZS
[J]. APPLIED INTELLIGENCE, 2003, 18 (01) : 37 - 54
[49] The interchangeability of learning rate and gain in backpropagation neural networks
Thimm, G
Moerland, P
Fiesler, E
[J]. NEURAL COMPUTATION, 1996, 8 (02) : 451 - 460
[50] A novel learning algorithm for feedforward neural networks
Chen, Huawei
Jin, Fan
[J]. ADVANCES IN NEURAL NETWORKS - ISNN 2006, PT 1, 2006, 3971 : 509 - 514

← 1 2 3 4 5 →