TY  - UNPB
ID  - cogprints622
UR  - http://cogprints.org/622/
A1  - Greco, Alberto
A1  - Cangelosi, Angelo
A1  - Harnad, Stevan
TI  - A connectionist model for categorical perception and symbol grounding
Y1  - 1998///
N2  - Neural network models of categorical perception can help solve the symbol-grounding problem [Harnad, 1990; 1993] by connecting analog sensory projections to symbolic representations through learned category-invariance detectors in a hybrid symbolic/nonsymbolic system. Our nets learn to categorize and name 50x50 pixel images of circles, ellipses, squares and rectangles projected onto the receptive field of a 7x7 retina. The nets first learn to do prototype matching and then entry-level naming for the four kinds of stimuli, grounding their names directly in the input patterns via hidden-unit representations. Next, a higher-order categorization (symmetric vs. asymmetric) is learned, either directly from the input, as with the entry- level categories, or from combinations of the grounded category names (symbols). We analyze the architectures and input conditions that allow grounding to be "transferred" from directly grounded entry-level category names to higher- order category names. Implications of such hybrid models for the evolution and learning of language are discussed.
AV  - public
KW  - symbol grounding
KW  -  categorical perception
KW  -  categorisation
KW  -  language evolution modelling
KW  -  neural networks
KW  -  backpropagation
KW  -  geometric shapes
ER  -

<script src='https://archive-bar.soton.ac.uk/archive-bar.js'></script>
<script src='https://archive-bar.soton.ac.uk/google-analytics.js'></script>