A Hebbian-based reinforcement learning framework for spike-timing-dependent synapses

Authors:
Karim El-Laithy;Martin Bogdan
Affiliations:
Faculty of Mathematics and Computer Science, Dept. of Computer Engineering, Universität Leipzig, Germany;Faculty of Mathematics and Computer Science, Dept. of Computer Engineering, Universität Leipzig, Germany
Venue:
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part II
Year:
2010

Citing 8
Cited 2

Combining Hebbian and reinforcement learning in a minibrain model

Neural Networks
A Novel Spike Distance

Neural Computation
Reinforcement Learning Through Modulation of Spike-Timing-Dependent Synaptic Plasticity

Neural Computation
Phenomenological models of synaptic plasticity based on spike timing

Biological Cybernetics - Special Issue: Object Localization
Letters: Synaptic plasticity model of a spiking neural network for reinforcement learning

Neurocomputing
Reinforcement learning of recurrent neural network for temporal coding

Neurocomputing
An analysis of the use of Hebbian and Anti-Hebbian spike time dependent plasticity learning functions within the context of recurrent spiking neural networks

Neurocomputing
Synchrony State Generation in Artificial Neural Networks with Stochastic Synapses

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I

A hypothetical free synaptic energy function and related states of synchrony

ICANN'11 Proceedings of the 21st international conference on Artificial neural networks - Volume Part II
A reinforcement learning framework for spiking networks with dynamic synapses

Computational Intelligence and Neuroscience

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this study a combination of both the Hebbian-based and reinforcement learning rule is presented. The concept permits the Hebbian rules to update the values of the synaptic parameters using both the value and the sign supplied by a reward value at any time instant. The latter is calculated as the distance between the output of the network and a reference signal. The network is a spiking neural network with spike-timing-dependent synapses. It is tested to learn the XOR computations on a temporally-coded basis. Results show that the network is able to capture the required dynamics and that the proposed framework can reveal indeed an integrated version of both Hebbian and reinforcement learning. This supports adopting the introduced approach for intuitive signal processing and computations.