Title | ||
---|---|---|
Identification of Visual Features Using a Neural Version of Exploratory Projection Pursuit |
Abstract | ||
---|---|---|
We develop artificial neural networks which extract structure from visual data. We explore an extension of Hebbian Learning which has been called 驴 - Insensitive Hebbian Learning and show that it may be thought of as a special case of Maximum Likelihood Hebbian learning and investigate the resulting network with both real and artificial data. We show that the resulting network is able to identify a single orientation of bars from a mixture of horizontal and vertical bars and also it is able to identify local filters from video images. |
Year | Venue | Keywords |
---|---|---|
2002 | AICS | visual data,insensitive hebbian learning,special case,maximum likelihood hebbian learning,artificial data,hebbian learning,neural version,resulting network,local filter,single orientation,artificial neural network,exploratory projection pursuit,projection pursuit,maximum likelihood |
Field | DocType | Volume |
Competitive learning,Projection pursuit,Computer science,Unsupervised learning,Hebbian theory,Artificial intelligence,Artificial neural network,Generalized Hebbian Algorithm,Leabra,Special case | Conference | 2464 |
ISSN | ISBN | Citations |
0302-9743 | 3-540-44184-0 | 0 |
PageRank | References | Authors |
0.34 | 10 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Emilio Corchado | 1 | 2626 | 210.70 |
Colin Fyfe | 2 | 508 | 55.62 |