Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

Summer 1990, Vol. 2, No. 2, Pages 138-151
(doi: 10.1162/neco.1990.2.2.138)
© 1990 Massachusetts Institute of Technology
Distributed Symbolic Representation of Visual Shape
Article PDF (565.99 KB)
Abstract

The notion of distributed representation has gained significance in explanations of connectionist or “neural” networks. This communication shows that the concept also offers motivation in devising representations for visual shape within a symbolic computing paradigm. In a representation for binary (silhouette) shapes, and in analogy with conventional distributed connectionist networks, descriptive power is gained when microfeatures are available naming important spatial relationships in images. Our symbolic approach is introduced through a vocabulary of 31 “hand built” shape descriptors operating in the two-dimensional shape world of the dorsal fins of fishes.