Tuesday, December 23, 2008

Encoding meaning with high-dimensional random vectors

My friend/collaborator Ross Gayler sent me this link to a recent talk by our colleague Pentti Kanerva, at the Redwood Center of Theoretical Neuroscience. Pentti is a pioneer in the field of sparse distributed memory, a biologically plausible model of mental representation similar to the Multiply-Add-Permute architecture that Ross and I are working on. The presentation is very accessible and deals with the exciting and open question of what kinds of things suggested by the architecture of the brain, if we modeled them mathematically, could give some properties that we associate with mind?