A learning algorithm for feedback neural network chips
F.M.A. Salam, Yuanda Wang · 1991
A novel learning algorithm for dynamic continuous-time models of artificial neural networks (ANNs) is introduced. The authors apply the algorithm to their proposed neural network architecture and describe the learning procedure for a fabricated chip of the architecture. The learning algorithm was implemented in software on a PC; it interacts with the chip in real-time via a special-purpose interface. Experiments have been conducted where various images were stored and retrieved successfully.>