The CHIR Algorithm: A Generalization for Multiple-Output and Multilayered Networks

A new learning algorithm, learning by choice of int ern al repr esentations (CHIR), was recently int roduced. Th e basic version of thi s algoriths was developed for a two-layer, single-out put , feedforward network of binary neurons . This paper presents a generalized version of the CHIR algorithm th at is capable of t raining mult ipleoutput net works. A way to ada pt the algorit hm to mult ilayered feedforward networks is also presented. 'vVe test the new version on two typical learning tas ks: the combined paritysymmet ry problem and t he random problem (random associat ions). The dependence of the algori th m performance on the network size and on the learning parameters is st udied.