Arthur Nádas
IEEE Transactions on Neural Networks
We propose a new neural network structure that is compatible with silicon technology. This network has the feature that the learning parameter is embodied in the thresholds of MOSFET devices and is local in character. The network is shown to be capable of forming associations by example as well as exhibiting the desirable features of the Hopfield type networks. © 1989.
Arthur Nádas
IEEE Transactions on Neural Networks
Fahiem Bacchus, Joseph Y. Halpern, et al.
IJCAI 1995
Jehanzeb Mirza, Leonid Karlinsky, et al.
NeurIPS 2023
Guo-Jun Qi, Charu Aggarwal, et al.
IEEE TPAMI