Abstract | ||
---|---|---|
. In previous work[1] it was shown that a mechanism competingfor a presynaptic factor enables the self-organizing formation of localreceptive fields with orientation selectivity, even though the synapses betweenthe input and output layers are all nonlocal, i.e., fully connected.The previous model, however, assumed a priori competitive systems,called hypercolumns, that may not appropriately represent the inherentstructure of the input, which is a hierarchy of lowto high-level features.... |
Year | DOI | Venue |
---|---|---|
1997 | 10.1007/BFb0032511 | IWANN |
Keywords | Field | DocType |
receptive fields,self-organizing formation,competitive systems,self organization,receptive field | Receptive field,Synapse,Pattern recognition,Computer science,A priori and a posteriori,Input/output,Learning rule,Artificial intelligence,Hierarchy,Synaptic weight | Conference |
Volume | ISSN | ISBN |
1240 | 0302-9743 | 3-540-63047-3 |
Citations | PageRank | References |
0 | 0.34 | 1 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Satoshi Maekawa | 1 | 27 | 4.94 |
Hidefumi Sawai | 2 | 69 | 18.04 |