Abstract | ||
---|---|---|
The way information is represented and processed in a neural network may have important consequences on its computational power and complexity. Basically, information representation refers to dis- tributed or localist encoding and information processing refers to schemes of connectivity that can be complete or minimal. In the past, theoretical and biologically inspired approaches of neural computation have insisted on complementary views (respectively distributed and complete versus localist and minimal) with complementary arguments (complexity ver- sus expressiveness). In this paper, we report experiments on biologically inspired neural networks performing sensorimotor coordination that in- dicate that a localist and minimal view may have good performances if some connectivity constraints (also coming from biological inspiration) are respected. |
Year | Venue | Keywords |
---|---|---|
2004 | ESANN | neural network,information processing |
Field | DocType | Citations |
Biological inspiration,Information processing,Computer science,Models of neural computation,Theoretical computer science,Artificial intelligence,Modular design,Artificial neural network,Machine learning,Information representation,Encoding (memory),Expressivity | Conference | 0 |
PageRank | References | Authors |
0.34 | 2 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Julien Vitay | 1 | 90 | 10.36 |
Nicolas P. Rougier | 2 | 106 | 14.78 |
Frédéric Alexandre | 3 | 82 | 15.94 |