Multi-class pattern classification using neural networks

Multi-class pattern classification has many applications including text document classification, speech recognition, object recognition, etc. Multi-class pattern classification using neural networks is not a trivial extension from two-class neural networks. This paper presents a comprehensive and co...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Pattern recognition Ročník 40; číslo 1; s. 4 - 18
Hlavní autoři: Ou, Guobin, Murphey, Yi Lu
Médium: Journal Article
Jazyk:angličtina
Vydáno: Oxford Elsevier Ltd 2007
Elsevier Science
Témata:
Applied sciences
Artificial intelligence
Coding, codes
Computer science; control theory; systems
Connectionism. Neural networks
Exact sciences and technology
Information, signal and communications theory
Machine learning
Multi-class classification
Neural networks
Pattern recognition
Signal and communications theory
Signal processing
Speech processing
Telecommunications and information theory
Multi-class classification
Pattern recognition
Neural networks
Machine learning
System architecture
Network architecture
Neural network
Object recognition
Modeling
Implementation
Learning
Coding
Pattern classification
Object detection
Speech recognition
Open market
Time complexity
Speech processing
Target detection
ISSN:0031-3203, 1873-5142
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Multi-class pattern classification has many applications including text document classification, speech recognition, object recognition, etc. Multi-class pattern classification using neural networks is not a trivial extension from two-class neural networks. This paper presents a comprehensive and competitive study in multi-class neural learning with focuses on issues including neural network architecture, encoding schemes, training methodology and training time complexity. Our study includes multi-class pattern classification using either a system of multiple neural networks or a single neural network, and modeling pattern classes using one-against-all, one-against-one, one-against-higher-order, and P-against- Q. We also discuss implementations of these approaches and analyze training time complexity associated with each approach. We evaluate six different neural network system architectures for multi-class pattern classification along the dimensions of imbalanced data, large number of pattern classes, large vs. small training data through experiments conducted on well-known benchmark data.
ISSN:0031-3203
1873-5142
DOI:10.1016/j.patcog.2006.04.041