Generalization in multi-layer networks of Sigma-pi units

W D Penny; T J Stonham

doi:10.1109/72.363490

Generalization in multi-layer networks of Sigma-pi units

W D Penny, T J Stonham

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

Abstract

This paper investigates a method for predicting the generalization error that a multi-layer network of Sigma-pi units will, on average, exhibit. Theoretical values are compared with those obtained by the computer simulation of small networks learning parity and contiguity functions.

Original language	English
Pages (from-to)	506-508
Number of pages	3
Journal	IEEE Transactions on Neural Networks
Volume	6
Issue number	2
DOIs	https://doi.org/10.1109/72.363490
Publication status	Published - 1995

Access to Document

10.1109/72.363490

Cite this

@article{fbcdaa4918be4ffa93129dc1899094ca,

title = "Generalization in multi-layer networks of Sigma-pi units",

abstract = "This paper investigates a method for predicting the generalization error that a multi-layer network of Sigma-pi units will, on average, exhibit. Theoretical values are compared with those obtained by the computer simulation of small networks learning parity and contiguity functions.",

author = "Penny, {W D} and Stonham, {T J}",

year = "1995",

doi = "10.1109/72.363490",

language = "English",

volume = "6",

pages = "506--508",

journal = "IEEE Transactions on Neural Networks",

issn = "1045-9227",

publisher = "The Institute of Electrical and Electronics Engineers (IEEE)",

number = "2",

}

TY - JOUR

T1 - Generalization in multi-layer networks of Sigma-pi units

AU - Penny, W D

AU - Stonham, T J

PY - 1995

Y1 - 1995

N2 - This paper investigates a method for predicting the generalization error that a multi-layer network of Sigma-pi units will, on average, exhibit. Theoretical values are compared with those obtained by the computer simulation of small networks learning parity and contiguity functions.

AB - This paper investigates a method for predicting the generalization error that a multi-layer network of Sigma-pi units will, on average, exhibit. Theoretical values are compared with those obtained by the computer simulation of small networks learning parity and contiguity functions.

U2 - 10.1109/72.363490

DO - 10.1109/72.363490

M3 - Article

C2 - 18263335

VL - 6

SP - 506

EP - 508

JO - IEEE Transactions on Neural Networks

JF - IEEE Transactions on Neural Networks

SN - 1045-9227

IS - 2

ER -