EXTEND CONNECTIONIST NETWORK MODELS TO DO SEQUENTIAL REASONING.

Y. C. Lee; H. H. Chen; G. Z. Sun; H. Y. Lee; Tom Maxwell; C. Lee Giles

EXTEND CONNECTIONIST NETWORK MODELS TO DO SEQUENTIAL REASONING.

Y. C. Lee, H. H. Chen, G. Z. Sun, H. Y. Lee, Tom Maxwell, C. Lee Giles

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Summary form only given, as follows. A neural blackboard architecture is proposed in which a high-order associative memory network serves as a global shared memory for one or more feedforward-type neural inference engines to allow the system to reason in a time-delayed, or sequential, manner. New learning algorithms are proposed to speed up slow learning and to partially alleviate the tough credit apportionment problem inherent in any multistep decision.

Original language	English (US)
Title of host publication	Unknown Host Publication Title
Publisher	IEEE
Pages	6
Number of pages	1
State	Published - 1987

All Science Journal Classification (ASJC) codes

General Engineering

Cite this

@inproceedings{3ba1d95871984389a84e18df915f9824,

title = "EXTEND CONNECTIONIST NETWORK MODELS TO DO SEQUENTIAL REASONING.",

abstract = "Summary form only given, as follows. A neural blackboard architecture is proposed in which a high-order associative memory network serves as a global shared memory for one or more feedforward-type neural inference engines to allow the system to reason in a time-delayed, or sequential, manner. New learning algorithms are proposed to speed up slow learning and to partially alleviate the tough credit apportionment problem inherent in any multistep decision.",

author = "Lee, {Y. C.} and Chen, {H. H.} and Sun, {G. Z.} and Lee, {H. Y.} and Tom Maxwell and Giles, {C. Lee}",

year = "1987",

language = "English (US)",

pages = "6",

booktitle = "Unknown Host Publication Title",

publisher = "IEEE",

}

TY - GEN

T1 - EXTEND CONNECTIONIST NETWORK MODELS TO DO SEQUENTIAL REASONING.

AU - Lee, Y. C.

AU - Chen, H. H.

AU - Sun, G. Z.

AU - Lee, H. Y.

AU - Maxwell, Tom

AU - Giles, C. Lee

PY - 1987

Y1 - 1987

N2 - Summary form only given, as follows. A neural blackboard architecture is proposed in which a high-order associative memory network serves as a global shared memory for one or more feedforward-type neural inference engines to allow the system to reason in a time-delayed, or sequential, manner. New learning algorithms are proposed to speed up slow learning and to partially alleviate the tough credit apportionment problem inherent in any multistep decision.

AB - Summary form only given, as follows. A neural blackboard architecture is proposed in which a high-order associative memory network serves as a global shared memory for one or more feedforward-type neural inference engines to allow the system to reason in a time-delayed, or sequential, manner. New learning algorithms are proposed to speed up slow learning and to partially alleviate the tough credit apportionment problem inherent in any multistep decision.

UR - http://www.scopus.com/inward/record.url?scp=0023538671&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0023538671&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0023538671

SP - 6

BT - Unknown Host Publication Title

PB - IEEE

ER -

EXTEND CONNECTIONIST NETWORK MODELS TO DO SEQUENTIAL REASONING.

Abstract

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this