Neural network capacity using delta rule
D.L. Prados, Subhash C. Kak · Electronics Letters · 1989
It is shown that modifying the Hopfield neural network model to use the delta rule rather than the Hebbian rule substantially increases the capacity. The number of patterns one can store in a neural network of N neurons is actually greater than N (unless N is very small). For example, for N = 30, one can store 40 patterns with a success rate of close to 90%.