We describe a neural network able to rapidly establish cor- respondence between neural fields. The network is based on a cortical columnar model described earlier. It realizes dynamic links with the help of specialized columns that evaluate similarities between the activity dis- tributions of local feature cell populations, are subject to a topology con- straint, and gate the transfer of feature information between the neural fields. Correspondence finding requires little time (estimated to 10-40ms in physiological terms) and is robust to noise in feature signals.
Mendeley saves you time finding and organizing research
Choose a citation style from the tabs below