A biologically plausible learning method for neurorobotic systems

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.