The research on learning algorithm of binary neural networks
Qiang Hua, Qi-Lun Zheng · 2003
HGLA (Hamming-graph learning algorithm) is an unexhausted learning algorithm of binary neural networks. It affords the methods of using hidden neurons to express the most number of samples; the formula to calculate the weights and threshold; and the output neuron needs no training, so it is optimized.