This work deals with a problem of synthesis of the artificial neural networks using the evolutional scanning method. The basic task to be solved is to create a symbolic regression algorithm on principles of analytic programming, which will be capable of performing a convenient neural network synthesis. The main motivation here is the computerization of such synthesis and discovering so far unknown solutions.
Citation:
Zelinka Ivan, Varacha Pavel, "Synthesis of artificial neural networks by evolutionary methods," dexa, pp.153-157, 18th International Conference on Database and Expert Systems Applications (DEXA 2007), 2007