Abstract | ||
---|---|---|
Cook (1995) criticizes the work of Jacobs and Kosslyn (1994) on spatial relations, shape representations, and receptive fields in neural network models on the grounds that first-order correlations between input and output unit activities can explain the results. We reply briefly to Cook's arguments here (and in Kosslyn, Chabris, Marsolek, Jacobs & Koenig, 1995) and discuss how new simulations can confirm the importance of receptive field size as a crucial variable in the encoding of categorical and coordinate spatial relations and the corresponding shape representations; such simulations would testify to the computational distinction between the different types of representations. |
Year | DOI | Venue |
---|---|---|
1995 | 10.1016/0364-0213(95)90011-X | Cognitive Science |
Keywords | Field | DocType |
first order,spatial relation,receptive field,neural network model | Receptive field,Spatial relation,Categorical variable,Cognitive psychology,Psychology,Input/output,Artificial neural network,Cognition,Connectionism,Encoding (memory) | Journal |
Volume | Issue | ISSN |
19 | 4 | 0364-0213 |
Citations | PageRank | References |
2 | 0.54 | 2 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Stephen M. Kosslyn | 1 | 70 | 83.11 |
Christopher F. Chabris | 2 | 47 | 10.69 |
David P. Baker | 3 | 117 | 14.08 |