Title | ||
---|---|---|
A hierarchical generative model of recurrent object-based attention in the visual cortex |
Abstract | ||
---|---|---|
In line with recent work exploring Deep Boltzmann Machines (DBMs) as models of cortical processing, we demonstrate the potential of DBMs as models of object-based attention, combining generative principles with attentional ones. We show: (1) How inference in DBMs can be related qualitatively to theories of attentional recurrent processing in the visual cortex; (2) that deepness and topographic receptive fields are important for realizing the attentional state; (3) how more explicit attentional suppressive mechanisms can be implemented, depending crucially on sparse representations being formed during learning. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1007/978-3-642-21735-7_3 | ICANN (1) |
Keywords | Field | DocType |
cortical processing,hierarchical generative model,recurrent object-based attention,generative principle,object-based attention,deep boltzmann machines,attentional recurrent processing,visual cortex,sparse representation,topographic receptive field,attentional state,recent work,explicit attentional suppressive mechanism | Receptive field,Object-based attention,Visual cortex,Inference,Computer science,Sparse approximation,Reconstruction error,Artificial intelligence,Generative grammar,Machine learning,Generative model | Conference |
Volume | ISSN | Citations |
6791 | 0302-9743 | 7 |
PageRank | References | Authors |
0.67 | 4 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
David P. Reichert | 1 | 88 | 6.85 |
Peggy Series | 2 | 14 | 1.66 |
Amos J. Storkey | 3 | 955 | 94.20 |