Stabilising Hebbian Learning with a Third Factor in a Food Retrieval Task
When neurons fire together they wire together. This is Donald Hebb’s famous postulate. However, Hebbian learning is inherently unstable because synaptic weights will self amplify themselves: the more a synapse is able to drive a postsynaptic cell the more the synaptic weight will grow. We present a new biologically realistic way how to stabilise synaptic weights by introducing a third factor which switches on or off learning so that self amplification is minimised. The third factor can be identified by the activity of dopaminergic neurons in VTA which fire when a reward has been encountered. This leads to a new interpretation of the dopamine signal which goes beyond the classical prediction error hypothesis. The model is tested by a real world task where a robot has to find “food disks” in an environment.
KeywordsConditioned Stimulus Synaptic Weight Lateral Hypothalamus Real Robot Successful Learning
Unable to display preview. Download preview PDF.
- 1.Hebb, D.O.: The organization of behavior: A neurophychological study. Wiley-Interscience, New York (1949)Google Scholar
- 2.Kosco, B.: Differential hebbian learning. In: Denker, J.S. (ed.) Neural Networks for computing. AIP conference proceedings, Snowbird, Utah, vol. 151, pp. 277–282. American Institute of Physics, New York (1986)Google Scholar
- 8.Ziemke, T.: Are robots embodied? In: First international workshop on epigenetic robotics Modeling Cognitive Development in Robotic Systems, Lund, vol. 85 (2001)Google Scholar
- 9.Sutton, R.: Learning to predict by method of temporal differences. Machine Learning 3(1), 9–44 (1988)Google Scholar
- 10.Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2002th edn. Bradford Books, MIT Press (1998)Google Scholar
- 18.Prescott, T.J., González, F.M.M., Gurney, K., Humpries, M.D., Redgrave, P.: A robot model of the basal ganglia: Behaviour and intrinsic processing. Neural Networks (in press, 2006)Google Scholar