Cmos Implementation of an Artificial Nueron Learnable to Arbitrary Logical Functions

The paper offers a new methodology of designing in CMOS technology analogdigital artificial neurons learnable to arbitrary logical threshold functions of some number of variables. The problems of functional ability, implementability restrictions, noise stability, and refreshment of the learned state are formulated and solved. Some functional problems in experiments on teaching an artificial neuron to logical functions are considered. Recommendations on selection of testing functions and formation of teaching sequences are given. All results in the paper are received using SPICE simulation. For simulation experiments with analog/digital CMOS circuits, the transistor models MOSIS BSIM3v3.1, 0.8μm, level 7 are used. Key-Words: artificial neuron, CMOS implementation, learnable synapse, excitatory and inhibitory inputs, learning process, learning sequence, refreshment process, test function, threshold logical element, threshold logical function, Horner's scheme, Fibonacci sequence.