skip to content
The perceptron strikes back Preview this item
ClosePreview this item
Checking...

The perceptron strikes back

Author: Richard Beigel; Nick Reingold; Daniel Spielman
Publisher: New Haven, Conn. : Yale University, Dept. of Computer Science, [1990]
Series: Yale University.; Department of Computer Science.; Technical report
Edition/Format:   Book : English
Database:WorldCat
Summary:
Abstract: "We show that circuits composed of a symmetric gate at the root with AND-OR subcircuits of constant depth can be simulated by probabilistic depth-2 circuits with essentially the same symmetric gate at the root and AND gates of small fanin at the bottom. In particular, every language recognized by a depth-d AC⁰ circuit is decidable by a probabilistic perceptron of size 2[superscript O(log 5d n)] and order  Read more...
Rating:

(not yet rated) 0 with reviews - Be the first.

Subjects
More like this

 

Find a copy in the library

&AllPage.SpinnerRetrieving; Finding libraries that hold this item...

Details

Document Type: Book
All Authors / Contributors: Richard Beigel; Nick Reingold; Daniel Spielman
OCLC Number: 25999718
Notes: "September 11, 1990."
Description: 7 leaves ; 28 cm.
Series Title: Yale University.; Department of Computer Science.; Technical report
Responsibility: Richard Beigel, Nick Reingold, Daniel Spielman.

Abstract:

Abstract: "We show that circuits composed of a symmetric gate at the root with AND-OR subcircuits of constant depth can be simulated by probabilistic depth-2 circuits with essentially the same symmetric gate at the root and AND gates of small fanin at the bottom. In particular, every language recognized by a depth-d AC⁰ circuit is decidable by a probabilistic perceptron of size 2[superscript O(log 5d n)] and order O(log[superscript 5d] n) that uses O(log³n) probabilistic bits. As a corollary, we present a new proof that depth-d AND-OR circuits computing the parity of n binary inputs require size 2[superscript n omega](1/d)]."

Reviews

User-contributed reviews
Retrieving GoodReads reviews...
Retrieving DOGObooks reviews...

Tags

Be the first.

Similar Items

Confirm this request

You may have already requested this item. Please select Ok if you would like to proceed with this request anyway.

Linked Data


<http://www.worldcat.org/oclc/25999718>
library:oclcnum"25999718"
library:placeOfPublication
library:placeOfPublication
owl:sameAs<info:oclcnum/25999718>
rdf:typeschema:Book
schema:about
schema:about
schema:about
schema:about
<http://id.worldcat.org/fast/871991>
rdf:typeschema:Intangible
schema:name"Computational complexity"@en
schema:name"Computational complexity."@en
schema:contributor
schema:contributor
schema:creator
schema:datePublished"1990"
schema:description"Abstract: "We show that circuits composed of a symmetric gate at the root with AND-OR subcircuits of constant depth can be simulated by probabilistic depth-2 circuits with essentially the same symmetric gate at the root and AND gates of small fanin at the bottom. In particular, every language recognized by a depth-d AC⁰ circuit is decidable by a probabilistic perceptron of size 2[superscript O(log 5d n)] and order O(log[superscript 5d] n) that uses O(log³n) probabilistic bits. As a corollary, we present a new proof that depth-d AND-OR circuits computing the parity of n binary inputs require size 2[superscript n omega](1/d)].""@en
schema:exampleOfWork<http://worldcat.org/entity/work/id/29116765>
schema:inLanguage"en"
schema:name"The perceptron strikes back"@en
schema:publisher
schema:url

Content-negotiable representations

Close Window

Please sign in to WorldCat 

Don't have an account? You can easily create a free account.