Multi-modular neural network-hybrid architectures: a review

Multi-modular neural network-hybrid architectures: a review

A formalism to train multi-modular architectures (MMAs) is given. Examples of MMAs for various applications in image and speech processing are shown, which illustrate the benefits of using MMAs.

Saved in:
Bibliographic Details
Published in:International Joint Conference on Neural Networks, Nagoya, 1993 Vol. 3; pp. 2231 - 2236 vol.3
Main Author: Fogelman Soulie, F.
Format: Conference Proceeding Journal Article
Language:English
Published: IEEE 1993
Subjects:
Computer architecture
Cost function
Insulation
Lagrangian functions
Neural networks
Optical character recognition software
Optical computing
Speech processing
Speech recognition
Transfer functions
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A formalism to train multi-modular architectures (MMAs) is given. Examples of MMAs for various applications in image and speech processing are shown, which illustrate the benefits of using MMAs.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISBN:0780314212
9780780314214
DOI:10.1109/IJCNN.1993.714170