- Ph.D., Electrical Engineering, Stanford University
- M.S., Mathematics, Stanford University
- M.S., Electrical Engineering, Stanford University
- B.S., Electrical Engineering, California Institute of Technology
Early papers focused on artificial neural networks. Major themes were learning in fixed-weight networks and universal approximation by spiking neural networks. Current work involves characterizing transfer functions of spiking neural networks.
Neil Cotter has taught at the University of Utah for the past 30 years. His current teaching assignments are in the area of electronics and probability and statistics. In the past, he has taught a wide variety of classes in areas such as MATLAB programming, digital electronics, communication systems, control theory, optimization, and function approximations. He was educated at Caltech and Stanford, receiving a Ph.D. in electrical engineering and M.S. degrees in both electrical engineering and mathematics at the latter. His primary area of technical interest is nonlinear adaptive systems, especially spiking neural networks.