Multi-associative neural networks and their applications to learning and retrieving complex spatio-temporal sequences
Based on the previous work of a number of authors, we discuss an important class of neural networks which we call multi-associative neural networks (MANNs) and which associate one pattern with multiple patterns. As a computationally efficient example of such networks, we describe a specific MANN, th...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2012
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/84922 http://hdl.handle.net/10220/8197 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-84922 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-849222020-03-07T13:57:21Z Multi-associative neural networks and their applications to learning and retrieving complex spatio-temporal sequences Wang, Lipo. School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering Based on the previous work of a number of authors, we discuss an important class of neural networks which we call multi-associative neural networks (MANNs) and which associate one pattern with multiple patterns. As a computationally efficient example of such networks, we describe a specific MANN, that is, a multi-associative, dynamically generated variant of the counterpropagation network (MCPN). As an application of MANNs, we design a general system that can learn and retrieve complex spatio-temporal sequences with any MANN. This system consists of comparator units, a parallel array of MANNs, and delayed feedback lines from the output of the system to the neural network layer. During learning, pairs of sequences of spatial patterns are presented to the system and the system learns-to associate patterns at successive times in sequence. During retrieving, a cue sequence, which may be obscured by spatial noise and temporal gaps, causes the system to output the stored spatio-temporal sequence. We prove analytically that this system is capable of learning and generating any spatio-temporal sequences within the maximum complexity determined by the number of embedded MANNs, with the maximum length and number of sequences determined by the memory capacity of the embedded MANNs. To demonstrate the applicability of this general system, we present an implementation using the MCPN. The system shows desirable properties such as fast and accurate learning and retrieving, and ability to store a large number of complex sequences consisting of nonorthogonal spatial patterns Accepted version 2012-06-12T06:51:44Z 2019-12-06T15:53:41Z 2012-06-12T06:51:44Z 2019-12-06T15:53:41Z 1999 1999 Journal Article Wang, L. (1999). Multi-associative neural networks and their applications to learning and retrieving complex spatio-temporal sequences. IEEE Transactions on Systems, Man, and Cybernetics – Part B: Cybernetics, 29(1), 73-82. https://hdl.handle.net/10356/84922 http://hdl.handle.net/10220/8197 10.1109/3477.740167 en IEEE transactions on systems, man, and cybernetics – Part B: cybernetics © 1999 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: [http://dx.doi.org/10.1109/3477.740167]. 10 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
DRNTU::Engineering::Electrical and electronic engineering |
spellingShingle |
DRNTU::Engineering::Electrical and electronic engineering Wang, Lipo. Multi-associative neural networks and their applications to learning and retrieving complex spatio-temporal sequences |
description |
Based on the previous work of a number of authors, we discuss an important class of neural networks which we call multi-associative neural networks (MANNs) and which associate one pattern with multiple patterns. As a computationally efficient example of such networks, we describe a specific MANN, that is, a multi-associative, dynamically generated variant of the counterpropagation network (MCPN). As an application of MANNs, we design a general system that can learn and retrieve complex spatio-temporal sequences with any MANN. This system consists of comparator units, a parallel array of MANNs, and delayed feedback lines from the output of the system to the neural network layer. During learning, pairs of sequences of spatial patterns are presented to the system and the system learns-to associate patterns at successive times in sequence. During retrieving, a cue sequence, which may be obscured by spatial noise and temporal gaps, causes the system to output the stored spatio-temporal sequence. We prove analytically that this system is capable of learning and generating any spatio-temporal sequences within the maximum complexity determined by the number of embedded MANNs, with the maximum length and number of sequences determined by the memory capacity of the embedded MANNs. To demonstrate the applicability of this general system, we present an implementation using the MCPN. The system shows desirable properties such as fast and accurate learning and retrieving, and ability to store a large number of complex sequences consisting of nonorthogonal spatial patterns |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Wang, Lipo. |
format |
Article |
author |
Wang, Lipo. |
author_sort |
Wang, Lipo. |
title |
Multi-associative neural networks and their applications to learning and retrieving complex spatio-temporal sequences |
title_short |
Multi-associative neural networks and their applications to learning and retrieving complex spatio-temporal sequences |
title_full |
Multi-associative neural networks and their applications to learning and retrieving complex spatio-temporal sequences |
title_fullStr |
Multi-associative neural networks and their applications to learning and retrieving complex spatio-temporal sequences |
title_full_unstemmed |
Multi-associative neural networks and their applications to learning and retrieving complex spatio-temporal sequences |
title_sort |
multi-associative neural networks and their applications to learning and retrieving complex spatio-temporal sequences |
publishDate |
2012 |
url |
https://hdl.handle.net/10356/84922 http://hdl.handle.net/10220/8197 |
_version_ |
1681039020107235328 |