DESIGN OF A CEREBELLAR MODEL ARITHMETIC COMPUTER WITH ADAPTIVE RESOLUTION AND ITS APPLICATION TO NONLINEAR SIGNAL-PROCESSING

A cerebellar model arithmetic computer (CMAC) with adaptive input spac e quantization is designed. The quantization intervals are compressed by the segmentation of weights in the region where the function to be learned changes rapidly, whereas those are extended by the integration in the region where the function changes slowly. The adaptive resolut ion technique reduces required memory space and improves learning spee d. Results of simulation studies on nonlinear signal processing proble ms are reported. A storage procedure for the weights and new criteria for the integration and segmentation are also reported.