Learning by Stimulation Avoidance as a Primary Principle of Spiking Neural Networks Dynamics

Practical implementation of the concept of reward has deep implications on what artificial-life based systems can learn and how they learn it. How can a system distinguish between useful behavior and harmful behavior? In this paper we implement reward/punishment as the removal/application of a stimulation to a recurrent spiking neural network with spike-timing dependent plasticity. This implementation embodies the concept of reward at the level of the neuron, making learning mechanisms ubiquitous to the network. We show that this low-level learning scales up to the network level: the network learns arbitrary spatio-temporal firing patterns purely by interacting with the environment, from a random initial state where virtually no knowledge is available. This approach yields fast, noise-robust results.