Fixed-point attractors in analog neural computation
F. R. Waugh, C. M. Marcus, R. M. Westervelt · Physical Review Letters · 1990
We show analytically that the expected number of fixed-point attractors in an associative memory neural network with analog neurons decreases exponentially as the neuron gain is reduced. Eliminating fixed-point attractors by using analog neurons has beneficial effects similar to stochastic annealing but can be easily implemented in a deterministic dynamical system such as an analog electronic circuit. Numerical data based on fixed-point counts in small networks support the analytical results.