IMI-BAS BAS
 

BulDML at Institute of Mathematics and Informatics >
ITHEA >
International Journal ITA >
2006 >
Volume 13 Number 2 >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10525/738

Title: Generalization by Computation Through Memory
Authors: Gopych, Petro
Keywords: Generalization
Grandmother Model for Vision
Neural Network Assembly Memory Model
One-Step Learning
Learning from one Example
Neuron Receptive Field
Bell-Shaped Tuning
Semi-Representation
Issue Date: 2006
Publisher: Institute of Information Theories and Applications FOI ITHEA
Abstract: Usually, generalization is considered as a function of learning from a set of examples. In present work on the basis of recent neural network assembly memory model (NNAMM), a biologically plausible 'grandmother' model for vision, where each separate memory unit itself can generalize, has been proposed. For such a generalization by computation through memory, analytical formulae and numerical procedure are found to calculate exactly the perfectly learned memory unit's generalization ability. The model's memory has complex hierarchical structure, can be learned from one example by a one-step process, and may be considered as a semi-representational one. A simple binary neural network for bell-shaped tuning is described.
URI: http://hdl.handle.net/10525/738
ISSN: 1313-0463
Appears in Collections:Volume 13 Number 2

Files in This Item:

File Description SizeFormat
ijita13-2-p07.pdf214.77 kBAdobe PDFView/Open

 



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Valid XHTML 1.0!   Creative Commons License DSpace Software Copyright © 2002-2009  The DSpace Foundation - Feedback