Journal
NEURAL NETWORKS
Volume 67, Issue -, Pages 1-13Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2015.03.002
Keywords
Spiking neurons; Basal ganglia; Reinforcement learning; Cognitive modeling; Action selection
Funding
- German Research Foundation [DFG HA2630/8-1, DFG HA2630/7-2 (KFO 247)]
Ask authors/readers for more resources
We introduce a splicing neural network of the basal ganglia capable of learning stimulus action associations. We model learning in the three major basal ganglia pathways, direct, indirect and hyperdirect, by spike time dependent learning and considering the amount of dopamine available (reward). Moreover, we allow to learn a cortico-thalamic pathway that bypasses the basal ganglia. As a result the system develops new functionalities for the different basal ganglia pathways: The direct pathway selects actions by disinhibiting the thalamus, the hyperdirect one suppresses alternatives and the indirect pathway learns to inhibit common mistakes. Numerical experiments show that the system is capable of learning sets of either deterministic or stochastic rules. (C) 2015 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available