Technical Note: \cal Q-Learning
Machine Learning
Actor-critic models of the basal ganglia: new anatomical and computational perspectives
Neural Networks - Computational models of neuromodulation
Learning to Predict by the Methods of Temporal Differences
Machine Learning
Spontaneous Dynamics of Asymmetric Random Recurrent Spiking Neural Networks
Neural Computation
Predictive Coding in Cortical Microcircuits
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
Computational Intelligence and Neuroscience
Hi-index | 0.01 |
This paper addresses the question of the functional role of the dual application of positive and negative Hebbian time dependent plasticity rules, in the particular framework of reinforcement learning tasks. Our simulations take place in a recurrent network of spiking neurons with inhomogeneous synaptic weights. A spike-timing dependent plasticity (STDP) rule is combined with its ''opposite'', the ''anti-STDP''. A local regulation mechanism moreover maintains the postsynaptic neuron in the vicinity of a reference frequency, which forces the global dynamics to be maintained in a softly disordered regime. This approach is tested on a simple discrimination task which requires short-term memory: temporal pattern classification. We show that such temporal patterns can be categorised, and present tracks for future improvements.