Limited Weights Neural Networks - Very Tight Entropy Based Bounds

Valeriu Beiu; Sorin Draghici

Limited Weights Neural Networks - Very Tight Entropy Based Bounds

Valeriu Beiu, Sorin Draghici

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

Abstract

Being given a set of m examples (i.e., data-set) from IR{sup n} belonging to k different classes, the problem is to compute the required number-of-bits (i.e., entropy) for correctly classifying the data-set. Very tight upper and lower bounds for a dichotomy (i.e., k = 2) will be presented, but they are valid for the general case.

Original language	English
Title of host publication	ICSC International Symposium on Soft Computing
Publisher	Millet : ICSC Academic Press
Publication status	Published - Dec 31 1997
Event	SOCO'97 - Nîmes, France Duration: Sept 17 1997 → …

Conference

Conference	SOCO'97
Period	9/17/97 → …

Cite this

@inproceedings{8ca4228709414c8e8c9fb09070ca788b,

title = "Limited Weights Neural Networks - Very Tight Entropy Based Bounds",

abstract = "Being given a set of m examples (i.e., data-set) from IR{sup n} belonging to k different classes, the problem is to compute the required number-of-bits (i.e., entropy) for correctly classifying the data-set. Very tight upper and lower bounds for a dichotomy (i.e., k = 2) will be presented, but they are valid for the general case.",

author = "Valeriu Beiu and Sorin Draghici",

year = "1997",

month = dec,

day = "31",

language = "English",

booktitle = "ICSC International Symposium on Soft Computing",

publisher = "Millet : ICSC Academic Press",

note = "SOCO'97 ; Conference date: 17-09-1997",

}

TY - GEN

T1 - Limited Weights Neural Networks - Very Tight Entropy Based Bounds

AU - Beiu, Valeriu

AU - Draghici, Sorin

PY - 1997/12/31

Y1 - 1997/12/31

N2 - Being given a set of m examples (i.e., data-set) from IR{sup n} belonging to k different classes, the problem is to compute the required number-of-bits (i.e., entropy) for correctly classifying the data-set. Very tight upper and lower bounds for a dichotomy (i.e., k = 2) will be presented, but they are valid for the general case.

AB - Being given a set of m examples (i.e., data-set) from IR{sup n} belonging to k different classes, the problem is to compute the required number-of-bits (i.e., entropy) for correctly classifying the data-set. Very tight upper and lower bounds for a dichotomy (i.e., k = 2) will be presented, but they are valid for the general case.

M3 - Conference contribution

BT - ICSC International Symposium on Soft Computing

PB - Millet : ICSC Academic Press

T2 - SOCO'97

Y2 - 17 September 1997

ER -

Limited Weights Neural Networks - Very Tight Entropy Based Bounds

Abstract

Conference

Fingerprint

Cite this