Low power VLSI neuron cells for artificial neural networks
Krzysztof W. Wawryn, Bogdan Strzeszewski · 2002
In this paper novel AB class neuron structures that set foundations for low power VLSI neural networks and other applications are proposed. The analog AB class building blocks for sigmoidal characteristic neuron cells and programmable weight synaptic connections are presented and discussed. A qualitative comparison is made between standard and proposed neuron cells.