Switching neural networks: A new connectionist model for classification

A new connectionist model, called Switching Neural Network (SNN), for the solution of classification problems is presented. SNN in- cludes a first layer containing a particular kind of A/D converters, called latticizers, that suitably transform input vectors into binary strings. Then, the subsequent two layers of an SNN realize a positive Boolean function that solve in a lattice domain the original classi¯cation problem. Every function realized by an SNN can be written in terms of intelligi- ble rules. Training can be performed by adopting a proper method for positive Boolean function reconstruction, called Shadow Clustering (SC). Simulation results obtained on the StatLog benchmark show the good quality of the SNNs trained with SC.