CNNOPT: Learning dynamics and CNN chip-specific robustness
Dániel Hillier, Samuel Xavier‐de‐Souza, Johan A. K. Suykens, Joos P. L. Vandewalle · 2006
A method is presented that unifies previous approaches with the aim of learning new templates with the ability to tune cellular nonlinear network (CNN) templates to individual chip instances in a global optimization framework. The proposed method is built on earlier approaches extending them in three main aspects. First, hardware parameters of the CNN chip are included in the optimization that opens the way to run templates so far believed to be very unstable on chip. Second, a novel global optimization algorithm is used that improves learning speed significantly. Third, the whole method is presented as a new Matlab toolbox so that the only task of the CNN algorithm designer is to formulate the operation to be learned as a training set of the optimization process. Training set design is the most crucial issue of this approach, thus basic rules for the design of training sets are presented. Examples are given in order to illustrate the design issues. We believe that the proposed method can be a valuable tool to find new CNN templates and robustly implement them on chip