Analog design of a new neural network for optical character recognition
I.P. Morns, S.S. Dlay · IEEE Transactions on Neural Networks · 1999
An electronic circuit is presented for a new type of neural network, which gives a recognition rate of over 100 kHz. The network is used to classify handwritten numerals, presented as Fourier and wavelet descriptors, and has been shown to train far quicker than the popular backpropagation network while maintaining classification accuracy.