A Hierarchical Learning System Incorporating with Supervised, Unsupervised and Reinforcement Learning

According to Hebb's Cell assembly theory, the brain has the capability of function localization. On the other hand, it is suggested that the brain has three different learning paradigms: supervised, unsupervised and reinforcement learning. Inspired by the above knowledge of brain, we present a hierarchical learning system consisting of three parts: supervised learning (SL) part, unsupervised learning (UL) part and reinforcement learning (RL) part. The SL part is a main part learning input-output mapping; the UL part realizes the function localization of learning system by controlling firing strength of neurons in SL part based on input patterns; the RL part optimizes system performance by adjusting parameters in UL part. Simulation results confirm the effectiveness of the proposed hierarchical learning system.

[1]  Kenji Doya,et al.  What are the computations of the cerebellum, the basal ganglia and the cerebral cortex? , 1999, Neural Networks.

[2]  F. Attneave,et al.  The Organization of Behavior: A Neuropsychological Theory , 1949 .

[3]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[4]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[5]  Jinglu Hu,et al.  Performance optimization of function localization neural network by using reinforcement learning , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[6]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[7]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[8]  Kotaro Hirasawa,et al.  Effective training methods for function localization neural networks , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[9]  K. Hirasawa,et al.  Self-organized function localization neural network , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).