Book
Sensory Neural Networks: Lateral Inhibition
1991
Abstract
Sensory information is detected and transformed by sensory neural networks before reaching higher levels of processing. These networks need to perform significant processing tasks while being compatible with the following levels. Lateral inhibition is a mechanism of local neuronal interaction that gives rise to significant global properties. This book studies visual sensory neural networks whose activity is governed by nonlinear lateral inhibition. It studies biological bases of models of lateral inhibition, computational properties of these models stressing their short term adaptive behavior, their relation to recent activity in neural networks and connectionist systems, their use for image processing applications, and their application to motion detection. Analog hardware implementation of these classes of networks are described in different technologies and results of implementation which corroborate theoretical analysis and show technologically desirable applications are presented.
Finally, nonlinear mathematical techniques are used to analyze temporal and spatial behavior of these models with the latter showing high order classification properties of the networks. As an interdisciplinary work, this book provides a consistent but multifaceted view which is useful for neural network theorists, biologists, circuit designers, and vision scientists.
Sensory information is detected and transformed by sensory neural networks before reaching higher levels of processing. These networks need to perform significant processing tasks while being compatible with the following levels. Lateral inhibition is a mechanism of local neuronal interaction that produces significant global properties. This book discusses those sensory neural networks influenced by nonlinear lateral inhibition. It features biological bases of lateral inhibition models, computational properties of these models that stress their short term adaptive behavior, their relation to recent activity in neural networks and connectionist systems, their use for image processing applications, and their application to motion detection. Descriptions from different technologies of analog hardware implementations of these classes of networks are described and results from implementations that corroborate theoretical analysis and show technologically desirable applications are presented. The book also uses nonlinear mathematical techniques to analyze temporal and spatial behavior of models presented within the text. Sensory Neural Networks: Lateral Inhibition is an interdisciplinary work that will prove useful to neural network theorists, biologists, circuit designers, and vision scientists.
Metrics
15 Record Views
Details
- Title
- Sensory Neural Networks: Lateral Inhibition
- Creators
- Bahrain Nabet - Drexel UniversityRobert B Pinter - University of Washington
- Publisher
- CRC Press
- Edition
- 1
- Number of pages
- 194
- Resource Type
- Book
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Scopus ID
- 2-s2.0-85051979089
- Other Identifier
- 9781138105461; 1138105465; 9781138561816; 1138561819; 020371041X; 9780203710418; 991019173700604721