1994
DOI: 10.1117/12.170003
|View full text |Cite
|
Sign up to set email alerts
|

<title>Dynamic perceptron: some theorems about the possibility of parallel pattern recognition with an application to high-energy physics</title>

Abstract: In the context of M.Minsky's and S.Papert's theorems on the impossibility of evaluating simple linear predicates by parallel architectures we want to show how these limitations can be avoided by introducing a generalized input-dependent preprocessing technique that does not suppose any a priori knowledge of input like in classical input filtering procedures. This technique can be formalized in a very general way and can be also deduced by meta-mathernatical arguments. A further development of the same techniqu… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

0
1
0

Year Published

1996
1996
1996
1996

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 1 publication
0
1
0
Order By: Relevance
“…5 -7 It has been shown that neural nets can accurately simulate any function. 6,7 Success has been attained in such diverse applications as handwriting recognition, high-energy physics, 8 and stockmarket prediction. In its simplest form a neural net (see Fig.…”
mentioning
confidence: 99%
“…5 -7 It has been shown that neural nets can accurately simulate any function. 6,7 Success has been attained in such diverse applications as handwriting recognition, high-energy physics, 8 and stockmarket prediction. In its simplest form a neural net (see Fig.…”
mentioning
confidence: 99%