N-dimensional coulomb neural network which provides for cumulative learning of internal representations

Claim 1

An N-dimensional Coulomb neural network comprising, in combination: (a) a plurality K of input terminals, each terminal (m) for receiving one of K input signals f m (t); (b) a plurality N of neural cells, each neural cell (n) having K inputs and one output, and for producing a first output signal x n (t) at its output representing a sum of K signal representations applied to its inputs; (c) a plurality N×K of input connection elements, each input connection element (mn) coupling one of said input terminals (m) with one of said neural cells (n) and providing a transfer of information from a respective input terminal (m) to a respective neural cell (n) in dependence upon a signal f m (t) appearing at an input terminal thereof and upon a connection strength ω nm of said connection element; (d) a plurality N of output connection elements, each output connection element (n) being coupled to said output of a respective one (n) of said neural cells and including: (1) means for storing said first output signal x n (t) of the neural cell (n) to which it is coupled; and (2) means for subtracting a next received first output signal x n (t+1) from a previously stored first output signal x n (t) to form a difference, and for producing a second output signal (x n (t)-x n (t+1)) 2 representing a square of said difference; (e) an effective cell connected to said output connection elements for receiving said second output signals and having means for computing a function of a state space distance, where L is an integer greater or equal to N-2, and for producing a third output signal representative thereof, wherein each of said neural cells adjusts a connection strength (ω nm ) in accordance with the formula: δω.sub.nm =(+/-)|x(t)-x(t+1)|-(L+2)Δ.sub.nm (f(t),f(t+1)) where Δ nm (f(t), f(t+1)) is given by: ##EQU21##