<> "The repository administrator has not yet configured an RDF license."^^ .
<> .
.
"Learning in the Cerebellum with Sparse Conjunctions and Linear Separator Algorithms"^^ .
"This paper investigates potential learning rules \nin the cerebellum. We review evidence that input to the cerebellum is \nsparsely expanded by granule cells into a very wide basis vector, \nand that Purkinje\ncells learn to compute a linear separation using that basis.\nWe review learning rules employed by existing cerebellar models, and show\nthat recent results from Computational Learning Theory suggest that\nthe standard delta rule would not be efficient.\nWe suggest that alternative, attribute-efficient learning rules, such as \nWinnow or Incremental Delta-Bar-Delta, are more appropriate for cerebellar\nmodeling, and support this position with results from a computational model.\n"^^ .
"2001" .
.
.
"IEEE"^^ .
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
"Kenneth"^^ .
"Marko"^^ .
"Kenneth Marko"^^ .
.
"Paul"^^ .
"Werbos"^^ .
"Paul Werbos"^^ .
.
"Harlan"^^ .
"Harris"^^ .
"Harlan Harris"^^ .
.
"Jesse"^^ .
"Reichler"^^ .
"Jesse Reichler"^^ .
.
.
.
.
.
"Learning in the Cerebellum with Sparse Conjunctions and Linear Separator Algorithms (Postscript)"^^ .
.
.
.
.
.
"sparsewinnow.ps"^^ .
.
"HTML Summary of #2310 \n\nLearning in the Cerebellum with Sparse Conjunctions and Linear Separator Algorithms\n\n" .
"text/html" .
.
.
"Computational Neuroscience" .
.
.
"Neural Modelling" .
.