Achievable Rates for Pattern Recognition

Biological and machine pattern recognition systems face a common challenge: Given sensory data about an unknown pattern, classify the pattern by searching for the best match within a library of representations stored in memory. In many cases, the number of patterns to be discriminated and the richne...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on information theory Ročník 54; číslo 1; s. 299 - 320
Hlavní autoři: Westover, M. Brandon, O'Sullivan, Joseph A.
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York, NY IEEE 01.01.2008
Institute of Electrical and Electronics Engineers
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Applied sciences
Classification
Coding, codes
Complexity
Conferences
Distributed source coding
Exact sciences and technology
Force sensors
Gaussian
Information processing
Information theory
Information, signal and communications theory
Libraries
Mathematical model
Mathematical models
Meetings
Memory
multiterminal information theory
Pattern matching
Pattern recognition
Pattern recognition systems
Preserves
Recognition
Representations
Signal and communications theory
Signal processing
Source coding
Telecommunications and information theory
multiterminal information theory
Source coding
Distributed source signal
Pattern recognition
Mathematical model
Information theory
Distributed source coding
pattern recognition
ISSN:0018-9448, 1557-9654
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Biological and machine pattern recognition systems face a common challenge: Given sensory data about an unknown pattern, classify the pattern by searching for the best match within a library of representations stored in memory. In many cases, the number of patterns to be discriminated and the richness of the raw data force recognition systems to internally represent memory and sensory information in a compressed format. However, these representations must preserve enough information to accommodate the variability and complexity of the environment, otherwise recognition will be unreliable. Thus, there is an intrinsic tradeoff between the amount of resources devoted to data representation and the complexity of the environment in which a recognition system may reliably operate. In this paper, we describe a mathematical model for pattern recognition systems subject to resource constraints, and show how the aforementioned resource-complexity tradeoff can be characterized in terms of three rates related to the number of bits available for representing memory and sensory data, and the number of patterns populating a given statistical environment. We prove single-letter information-theoretic bounds governing the achievable rates, and investigate in detail two illustrative cases where the pattern data is either binary or Gaussian.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ObjectType-Article-2
ObjectType-Feature-1
ISSN:0018-9448
1557-9654
DOI:10.1109/TIT.2007.911296