A COMPARISON STUDY OF BINARY FEEDFORWARD NEURAL NETWORKS AND DIGITAL CIRCUITS

被引：13

作者：

ANDREE, HMA ^{[1
]}

BARKEMA, GT ^{[1
]}

LOURENS, W ^{[1
]}

TAAL, A ^{[1
]}

VERMEULEN, JC ^{[1
]}

机构：

[1] NIKHEF H,AMSTERDAM,NETHERLANDS

来源：

NEURAL NETWORKS | 1993年 / 6卷 / 06期

关键词：

BINARY FEEDFORWARD NEURAL NETWORKS; LOGIC CIRCUITS; HARDWIRED IMPLEMENTATION;

D O I：

10.1016/S0893-6080(05)80123-6

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A comparison study was carried out between feedforward neural networks composed of binary linear threshold units and digital circuits. These networks were generated by the regular partitioning algorithm and a modified Quine-McCluskey algorithm, respectively. The size of both types of networks and their generalisation properties are compared as a function of the nearest-neighbour correlation in the binary input sets. The ratio of the number of components required by digital circuits and the number of neurons grows linearly for the input sets considered The considered neural networks do not outperform digital circuits with respect to generalisation. Sensitivity analysis leads to a preference for digital circuits, especially for increasing number of inputs. In the case of analog input sets, hybrid networks of binary neurons and logic gates are of interest.

引用

页码：785 / 790

页数：6

共 50 条

[1] Sensitivity study of Binary Feedforward Neural Networks
Huang, Lihong
Zeng, Xiaoqin
Zhong, Shuiming
Han, Lixin
NEUROCOMPUTING, 2014, 136 : 268 - 280
[2] A FAST PARTITIONING ALGORITHM AND A COMPARISON OF BINARY FEEDFORWARD NEURAL NETWORKS
KEIBEK, SAJ
BARKEMA, GT
ANDREE, HMA
SAVENIJE, MHF
TAAL, A
EUROPHYSICS LETTERS, 1992, 18 (06): : 555 - 559
[3] A TRAINING ALGORITHM FOR BINARY FEEDFORWARD NEURAL NETWORKS
GRAY, DL
MICHEL, AN
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (02): : 176 - 194
[4] ON THE DESIGN OF FEEDFORWARD NEURAL NETWORKS FOR BINARY MAPPINGS
TAN, SH
VANDEWALLE, J
NEUROCOMPUTING, 1994, 6 (5-6) : 565 - 582
[5] ANEFFICIENT LEARNING ALGORITHM FOR BINARY FEEDFORWARD NEURAL NETWORKS
Zhou, Jianxin
Zeng, Xiaoqin
Chan, Patrick P. K.
PROCEEDINGS OF 2015 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOL. 2, 2015, : 609 - 615
[6] An efficient learning algorithm for binary feedforward neural networks
Zeng X.
Zhou J.
Zheng X.
Zhong S.
Zhou, Jianxin (zhoujx0219@163.com), 2016, Harbin Institute of Technology (48): : 148 - 154
[7] ON THE DESIGN OF FEEDFORWARD NEURAL NETWORKS FOR BINARY MAPPING - COMMENTS
HSU, TC
WANG, SD
NEUROCOMPUTING, 1995, 9 (01) : 81 - 84
[8] Constructive training methods for feedforward neural networks with binary weights
Mayoraz, E
Aviolat, F
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 1996, 7 (02) : 149 - 166
[9] THE PATCH ALGORITHM - FAST DESIGN OF BINARY FEEDFORWARD NEURAL NETWORKS
BARKEMA, GT
ANDREE, HMA
TAAL, A
NETWORK-COMPUTATION IN NEURAL SYSTEMS, 1993, 4 (03) : 393 - 407
[10] NEURAL NETWORKS FOR DIGITAL SEQUENTIAL-CIRCUITS
NINOMIYA, H
ASAI, H
IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 1994, E77A (12) : 2112 - 2115

← 1 2 3 4 5 →