Analog Neural Networks of Limited Precision I: Computing with Multilinear Threshold Functions

Experimental evidence has shown analog neural networks to be ex(cid:173) mely fault-tolerant; in particular. Analog neurons with limited precision essentially compute k-ary weighted multilinear threshold functions. The behaviour of k-ary neural networks is investi(cid:173) gated. There is no canonical set of threshold values for k 3. although they exist for binary and ternary neural networks. The weights can be made integers of only 0 «z k) log (z k » bits.