STUDY OF A GROWTH ALGORITHM FOR A FEEDFORWARD NETWORK-Reference-Cited by-同舟云学术

STUDY OF A GROWTH ALGORITHM FOR A FEEDFORWARD NETWORK

Published:1989-01 Issue:01 Volume:01 Page:55-59
ISSN:0129-0657
Container-title:International Journal of Neural Systems
language:en
Short-container-title:Int. J. Neur. Syst.

Author:

Nadal Jean-Pierre¹

Affiliation:

1. Laboratoire de Physique Statistique (Laboratoire associé au C.N.R.S., U.R.A. 0731, et à l'Université Paris VI), Ecole Normale Supérieure, 24 rue Lhomond, F-75231 Paris Cedex 05, France

Abstract

We study an algorithm for a feedforward network which is similar in spirit to the Tiling algorithm recently introduced: the hidden units are added one by one until the network performs the desired task, and convergence is guaranteed. The difference is in the architecture of the network, which is more constrained here. Numerical tests show performances similar to that of the Tiling algorithm, although the total number of couplings in general grows faster.

Publisher

World Scientific Pub Co Pte Lt

Subject

Computer Networks and Communications,General Medicine

Link

https://www.worldscientific.com/doi/pdf/10.1142/S0129065789000463

Cited by 67 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Ensemble of heterogeneous flexible neural trees using multiobjective genetic programming;Applied Soft Computing;2017-03

2. Flexible Neural Trees—Parallel Learning on HPC;Advances in Intelligent Systems and Computing;2017

3. Self-learning Genetic Algorithm for Neural Network Topology Optimization;Agent and Multi-Agent Systems: Technologies and Applications;2015

4. Reverse engineering of gene regulatory networks using flexible neural tree models;Neurocomputing;2013-01

5. A LEMPEL-ZIV COMPLEXITY-BASED NEURAL NETWORK PRUNING ALGORITHM;International Journal of Neural Systems;2011-10