EVALUATION OF NETWORK ARCHITECTURES ON TEST LEARNING TASKS.

F. Fogelman Soulie, P. Gallinari, Yann LeCun, S. Thiria

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

Abstract

Two experiments with the gradient back propagation (GBP) algorithm have been carried out to determine how the architecture affects the performances of the network. The two examples have been designed to investigate two different properties of the networks: their memorization capacities and their ability to generalize by synthesizing appropriate predicates. The first experiment is an extension to the GBP algorithm of previous work comparing the memorization and generalization abilities of various network models on simple associative memory tasks. In the second experiment a network is taught to detect the presence of a given pattern in a signal.

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

Fingerprint

Network architecture
Backpropagation algorithms
Experiments
Data storage equipment

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Fogelman Soulie, F., Gallinari, P., LeCun, Y., & Thiria, S. (1987). EVALUATION OF NETWORK ARCHITECTURES ON TEST LEARNING TASKS. In M. Caudill, C. T. Butler, & S. D. Adaptics (Eds.), Unknown Host Publication Title SOS Printing.

EVALUATION OF NETWORK ARCHITECTURES ON TEST LEARNING TASKS. / Fogelman Soulie, F.; Gallinari, P.; LeCun, Yann; Thiria, S.

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

Fogelman Soulie, F, Gallinari, P, LeCun, Y & Thiria, S 1987, EVALUATION OF NETWORK ARCHITECTURES ON TEST LEARNING TASKS. in M Caudill, CT Butler & SD Adaptics (eds), Unknown Host Publication Title. SOS Printing.
Fogelman Soulie F, Gallinari P, LeCun Y, Thiria S. EVALUATION OF NETWORK ARCHITECTURES ON TEST LEARNING TASKS. In Caudill M, Butler CT, Adaptics SD, editors, Unknown Host Publication Title. SOS Printing. 1987
Fogelman Soulie, F. ; Gallinari, P. ; LeCun, Yann ; Thiria, S. / EVALUATION OF NETWORK ARCHITECTURES ON TEST LEARNING TASKS. Unknown Host Publication Title. editor / Maureen Caudill ; Charles T. Butler ; San Diego Adaptics. SOS Printing, 1987.
@inproceedings{b9b73c87bf7246608c92e8e99285a44c,
title = "EVALUATION OF NETWORK ARCHITECTURES ON TEST LEARNING TASKS.",
abstract = "Two experiments with the gradient back propagation (GBP) algorithm have been carried out to determine how the architecture affects the performances of the network. The two examples have been designed to investigate two different properties of the networks: their memorization capacities and their ability to generalize by synthesizing appropriate predicates. The first experiment is an extension to the GBP algorithm of previous work comparing the memorization and generalization abilities of various network models on simple associative memory tasks. In the second experiment a network is taught to detect the presence of a given pattern in a signal.",
author = "{Fogelman Soulie}, F. and P. Gallinari and Yann LeCun and S. Thiria",
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 - EVALUATION OF NETWORK ARCHITECTURES ON TEST LEARNING TASKS.

AU - Fogelman Soulie, F.

AU - Gallinari, P.

AU - LeCun, Yann

AU - Thiria, S.

PY - 1987

Y1 - 1987

N2 - Two experiments with the gradient back propagation (GBP) algorithm have been carried out to determine how the architecture affects the performances of the network. The two examples have been designed to investigate two different properties of the networks: their memorization capacities and their ability to generalize by synthesizing appropriate predicates. The first experiment is an extension to the GBP algorithm of previous work comparing the memorization and generalization abilities of various network models on simple associative memory tasks. In the second experiment a network is taught to detect the presence of a given pattern in a signal.

AB - Two experiments with the gradient back propagation (GBP) algorithm have been carried out to determine how the architecture affects the performances of the network. The two examples have been designed to investigate two different properties of the networks: their memorization capacities and their ability to generalize by synthesizing appropriate predicates. The first experiment is an extension to the GBP algorithm of previous work comparing the memorization and generalization abilities of various network models on simple associative memory tasks. In the second experiment a network is taught to detect the presence of a given pattern in a signal.

UR - http://www.scopus.com/inward/record.url?scp=0023538599&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0023538599&partnerID=8YFLogxK

M3 - Conference contribution

BT - Unknown Host Publication Title

A2 - Caudill, Maureen

A2 - Butler, Charles T.

A2 - Adaptics, San Diego

PB - SOS Printing

ER -