Title :
Adaptive tiled Neural Networks
Author :
Nokhbeh-Zaeem, Mohammad ; Khashabi, Daniel ; Talebi, H.A. ; Navabi, Sh. ; Jabbarvaziri, F.
Author_Institution :
Dept. of Electr. Eng., Amirkabir Univ. of Technol., Tehran, Iran
Abstract :
In this paper, a novel function approximation approach based on a combination of conventional Neural Networks and tile coding approximators is proposed. The proposed approach can maintain the desired features of both approaches whiles eliminates the deficiencies of each method. The combination will reduce the sharpness of tile coding. It will also provide an easy way to adjust the accuracy/complexity of the approximation according to the function being approximated (adaptive tiling) and the subspace used on. In this algorithm, it is possible to construct the approximator with specified and various approximation accuracies in different subspaces. This feature enables us to allocate an arbitrary accuracy/complexity wherever a more accurate approximation is needed. Finally simulation studies are presented to show the efficiency of and applicability of the proposed approach.
Keywords :
computational complexity; function approximation; mathematics computing; neural nets; adaptive tiled neural networks; computational complexity; function approximation; tile coding approximators; Accuracy; Artificial neural networks; Encoding; Function approximation; Tiles; Training; adaptive tile coding; adaptive tiling; approximation memory; neural network; tile coding;
Conference_Titel :
Systems, Man, and Cybernetics (SMC), 2011 IEEE International Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
978-1-4577-0652-3
DOI :
10.1109/ICSMC.2011.6084059