Title :
A biologically plausible learning method for neurorobotic systems
Author :
Davoudi, Heydar ; Vahdat, Bijan Vosoughi
Author_Institution :
Electr. Eng. Dept., Sharif Univ. of Technol., Tehran
fDate :
April 29 2009-May 2 2009
Abstract :
This paper introduces an incremental local learning algorithm inspired by learning in neurobiological systems. This algorithm has no training phase and learns the world during operation, in a lifetime manner. It is a semi-supervised algorithm which combines soft competitive learning in input space and linear regression with recursive update in output space. This method is also robust to negative interference and compromises bias-variance dilemma. These qualities make the learning method a good nonlinear function approximator having possible applications in neuro-robotic systems. Some simulations illustrate the effectiveness of the proposed algorithm in function approximation, time-series prediction, and motor control problems.
Keywords :
learning (artificial intelligence); medical robotics; neurophysiology; regression analysis; linear regression; local learning algorithm; motor control problems; neurorobotic systems; nonlinear function approximator; semisupervised algorithm; soft competitive learning; time-series prediction; Biological system modeling; Function approximation; Humans; Interference; Learning systems; Linear regression; Motor drives; Shape; Space technology; Statistical learning; function approximation; lifetime learning; neuro-robotics; statistical learning;
Conference_Titel :
Neural Engineering, 2009. NER '09. 4th International IEEE/EMBS Conference on
Conference_Location :
Antalya
Print_ISBN :
978-1-4244-2072-8
Electronic_ISBN :
978-1-4244-2073-5
DOI :
10.1109/NER.2009.5109251