Neural network synthesis by means of analytic programming-preliminary results
Ivan Zelinka, Eva Volná · Repository of TBU publications (Univerzita Tomase Bati ze Zline) · 2005
This contribution is introducing use of a novelty method, which allows solving various problems from symbolic regression domain. An idea of symbolic regression was firstly proposed by J. R. Koza in so called genetic programming and by C. Ryan in grammatical evolution. In this contribution is demonstrated use of novelty method called analytical programming on neural network synthesis.