Geoffrey Grinstein, Ralph Linsker
PNAS
This note presents a local learning rule that enables a network to maximize the mutual information between input and output vectors. The network's output units may be nonlinear, and the distribution of input vectors is arbitrary. The local algorithm also serves to compute the inverse C-1 of an arbitrary square connection weight matrix.
Geoffrey Grinstein, Ralph Linsker
PNAS
Alina Beygelzimer, Geoffrey Grinstein, et al.
ICAC 2004
Ralph Linsker
IJCNN 2009
Ralph Linsker, R. Srinivasan, et al.
Lasers in Surgery and Medicine