A modified Hamming neural network with different thresholds and multi-valued weights
Wei Lu, Bingxue Shi, Zhi-Jian Li · 2002
A modified Hamming neural network and its integrated circuit model are presented, in which different thresholds and multi-valued weights are introduced. The network consists of a template matching circuit and a "winner-take-all" (WTA) circuit. Simulation shows that it has high precision, high speed and low power dissipation. It can be used to recognize handwritten digits.