Parallel implementation of the feedforward back-propagation algorithm on pyramid networks

被引：0
|
作者：
Maelainin, SA
Bellaachia, A
机构：
来源：
PARALLEL AND DISTRIBUTED COMPUTING SYSTEMS - PROCEEDINGS OF THE ISCA 9TH INTERNATIONAL CONFERENCE, VOLS I AND II | 1996年
关键词：
pyramid; interconnection networks; neural networks; backpropagation; feedforward; hopfield network;
D O I：
暂无
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
In this paper, we present a parallel implementation of the FeedForward BackPropagation algorithm on pyramids. The proposed algorithm is quite simple and easy to implement. For an ANN of L layers and a maximum of N nodes per layer, our algorithm requires a pyramid of (4N(2)-1)/3 processors to perform backpropagation algorithm in O(LN) time complexity. Note that our solution requires less than the number of nodes required by the best known solution for a mesh of appendixed trees topology of 3N(2) processors. In addition, the algorithm can be adapted to quadtrees with slight modifications. The technique used in our implementation can also be applied to the Hopfield network.
引用
收藏
页码：444 / 449
页数：6
相关论文
共 50 条
  • [1] Parallel implementation of back-propagation algorithm in networks of workstations
    Suresh, S
    Omkar, SN
    Mani, V
    IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2005, 16 (01) : 24 - 34
  • [2] Hybrid Back-Propagation/Genetic Algorithm for multilayer feedforward neural networks
    Lu, C
    Shi, BX
    2000 5TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS I-III, 2000, : 571 - 574
  • [3] Boundedness and convergence of batch back-propagation algorithm with penalty for feedforward neural networks
    Zhang, Huisheng
    Wu, Wei
    Yao, Mingchen
    NEUROCOMPUTING, 2012, 89 : 141 - 146
  • [4] VLSI architecture for feedforward networks with integral back-propagation
    Paulos, John J.
    Hollis, Paul W.
    Neural Networks, 1988, 1 (1 SUPPL)
  • [5] GPU Implementation of the Multiple Back-Propagation Algorithm
    Lopes, Noel
    Ribeiro, Bernardete
    INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING, PROCEEDINGS, 2009, 5788 : 449 - 456
  • [6] Training Many Neural Networks in Parallel via Back-Propagation
    Cruz-Lopez, Javier A.
    Boyer, Vincent
    El-Baz, Didier
    2017 IEEE INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM WORKSHOPS (IPDPSW), 2017, : 501 - 509
  • [7] A HIGHLY EFFICIENT IMPLEMENTATION OF BACK-PROPAGATION ALGORITHM ON SIMD COMPUTERS
    CORANA, A
    ROLANDO, C
    RIDELLA, S
    HIGH PERFORMANCE COMPUTING /, 1989, : 181 - 190
  • [8] Parallel implementation of back-propagation neural network software on SMP computers
    Tsaregorodtsev, VG
    PARALLEL COMPUTING TECHNOLOGIES, 2005, 3606 : 186 - 192
  • [9] Infilling annual rainfall data using feedforward back-propagation Artificial Neural Networks (ANN): Application of the standard and generalised back-propagation techniques
    Ilunga, M.
    JOURNAL OF THE SOUTH AFRICAN INSTITUTION OF CIVIL ENGINEERING, 2010, 52 (01) : 2 - 10
  • [10] Generalized back-propagation algorithm with weight evolution for neural networks
    Ng, SC
    Leung, SH
    Luk, A
    6TH WORLD MULTICONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS, VOL XX, PROCEEDINGS EXTENSION, 2002, : 41 - 44
12345