A dual stage neural-network architecture is proposed, for the combined local and global processing of visual dot-patterns, in the spatial-orientational space. Dipoles defining local orientation are first determined by a Hopfield-type network. The second stage, consisting of a layered neural network, is then trained by the back propagation algorithm with a new cost function to discriminate between dipole patterns. The network performance in classification tasks is similar to that of human vision.
|State||Published - 1989|
|Event||16th Conference of Electrical and Electronics Engineers in Israel, EEIS 1989 - Tel-Aviv, Israel|
Duration: 7 Mar 1989 → 9 Mar 1989
|Conference||16th Conference of Electrical and Electronics Engineers in Israel, EEIS 1989|
|Period||7/03/89 → 9/03/89|