TIN: A TRAINABLE INFERENCE NETWORK.

C Larrabee Winter, T. W. Ryan, C. J. Turner

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

The Trainable Inference Network (TIN) is an adaptive network that can learn the functionality of any finite-state machine. TIN is composed of two modified adaptive resonance circuits (ARCs) that learn transition and output tables and an auxiliary assembly of control nodes that facilitates state transitions. The first ARC learns to recognize current-state, input, next-state patterns appearing on separate slabs; the other learns current-state, input, output patterns. Features of TIN's macrocircuit and dynamics are described, focusing on the first, state-transition ARC. TIN is then taught the states, input, and transitions of two simple finite-state machines. The results are summarized, and future research directions are indicated.

Original languageEnglish (US)
Title of host publicationUnknown Host Publication Title
EditorsMaureen Caudill, Charles T. Butler, San Diego Adaptics
PublisherSOS Printing
StatePublished - 1987
Externally publishedYes

Fingerprint

Circuit resonance
Finite automata

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Winter, C. L., Ryan, T. W., & Turner, C. J. (1987). TIN: A TRAINABLE INFERENCE NETWORK. In M. Caudill, C. T. Butler, & S. D. Adaptics (Eds.), Unknown Host Publication Title SOS Printing.

TIN : A TRAINABLE INFERENCE NETWORK. / Winter, C Larrabee; Ryan, T. W.; Turner, C. J.

Unknown Host Publication Title. ed. / Maureen Caudill; Charles T. Butler; San Diego Adaptics. SOS Printing, 1987.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Winter, CL, Ryan, TW & Turner, CJ 1987, TIN: A TRAINABLE INFERENCE NETWORK. in M Caudill, CT Butler & SD Adaptics (eds), Unknown Host Publication Title. SOS Printing.
Winter CL, Ryan TW, Turner CJ. TIN: A TRAINABLE INFERENCE NETWORK. In Caudill M, Butler CT, Adaptics SD, editors, Unknown Host Publication Title. SOS Printing. 1987
Winter, C Larrabee ; Ryan, T. W. ; Turner, C. J. / TIN : A TRAINABLE INFERENCE NETWORK. Unknown Host Publication Title. editor / Maureen Caudill ; Charles T. Butler ; San Diego Adaptics. SOS Printing, 1987.
@inproceedings{4c7234e528ff480288ddb113f3b91765,
title = "TIN: A TRAINABLE INFERENCE NETWORK.",
abstract = "The Trainable Inference Network (TIN) is an adaptive network that can learn the functionality of any finite-state machine. TIN is composed of two modified adaptive resonance circuits (ARCs) that learn transition and output tables and an auxiliary assembly of control nodes that facilitates state transitions. The first ARC learns to recognize current-state, input, next-state patterns appearing on separate slabs; the other learns current-state, input, output patterns. Features of TIN's macrocircuit and dynamics are described, focusing on the first, state-transition ARC. TIN is then taught the states, input, and transitions of two simple finite-state machines. The results are summarized, and future research directions are indicated.",
author = "Winter, {C Larrabee} and Ryan, {T. W.} and Turner, {C. J.}",
year = "1987",
language = "English (US)",
editor = "Maureen Caudill and Butler, {Charles T.} and Adaptics, {San Diego}",
booktitle = "Unknown Host Publication Title",
publisher = "SOS Printing",

}

TY - GEN

T1 - TIN

T2 - A TRAINABLE INFERENCE NETWORK.

AU - Winter, C Larrabee

AU - Ryan, T. W.

AU - Turner, C. J.

PY - 1987

Y1 - 1987

N2 - The Trainable Inference Network (TIN) is an adaptive network that can learn the functionality of any finite-state machine. TIN is composed of two modified adaptive resonance circuits (ARCs) that learn transition and output tables and an auxiliary assembly of control nodes that facilitates state transitions. The first ARC learns to recognize current-state, input, next-state patterns appearing on separate slabs; the other learns current-state, input, output patterns. Features of TIN's macrocircuit and dynamics are described, focusing on the first, state-transition ARC. TIN is then taught the states, input, and transitions of two simple finite-state machines. The results are summarized, and future research directions are indicated.

AB - The Trainable Inference Network (TIN) is an adaptive network that can learn the functionality of any finite-state machine. TIN is composed of two modified adaptive resonance circuits (ARCs) that learn transition and output tables and an auxiliary assembly of control nodes that facilitates state transitions. The first ARC learns to recognize current-state, input, next-state patterns appearing on separate slabs; the other learns current-state, input, output patterns. Features of TIN's macrocircuit and dynamics are described, focusing on the first, state-transition ARC. TIN is then taught the states, input, and transitions of two simple finite-state machines. The results are summarized, and future research directions are indicated.

UR - http://www.scopus.com/inward/record.url?scp=0023602772&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0023602772&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0023602772

BT - Unknown Host Publication Title

A2 - Caudill, Maureen

A2 - Butler, Charles T.

A2 - Adaptics, San Diego

PB - SOS Printing

ER -