Premium
Neural Network Models as Evidence for Different Types of Visual Representations
Author(s) -
Kosslyn Stephen M.,
Chabris Christopher F.,
Baker David P.
Publication year - 1995
Publication title -
cognitive science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.498
H-Index - 114
eISSN - 1551-6709
pISSN - 0364-0213
DOI - 10.1207/s15516709cog1904_5
Subject(s) - categorical variable , receptive field , cognitive science , variable (mathematics) , cognitive psychology , psychology , encoding (memory) , field (mathematics) , representation (politics) , computer science , artificial intelligence , mathematics , machine learning , pure mathematics , mathematical analysis , politics , political science , law
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.