Artificial neural device utilizing phase orientation in the complex number domain to encode and decode stimulus response patterns

Claim 1

In a plurality of computing nodes wherein each of said plurality communicates with others of said plurality by means of bidirectional serial communication means, and wherein each node comprises: (a) local memory storage means for storing data mapped onto said memory storage means; (b) micro-processing means including: (i) processor means; (ii) a plurality of data input means for receiving stimulus signals; (iii) a plurality of data output means for transmitting response signals; (iv) memory interface means for interfacing said micro-processing means with said local memory storage means; (c) said micro-processing means including: (i) means for encoding data onto said local memory storage means by translating sets of associated stimulus and response signals, received by said data input means from real values into a complex value represented by a vector phase angle and a magnitude exhibited within the generalized complex number domain and generating a matrix representing stimulus-response patterns for each set of associated stimulus and responses signals, whereby each said stimulus-response pattern is superimposed onto said local memory storage means; (ii) means operable for decoding a response, associated with a stimulus signal received by said data input means, from said matrix of stimulus-response patterns encoded on said local memory storage means, to generate a response signal associated with said stimulus signal through said data output means.