Theory of spike timing based neural classifiers

Abstract

We study the computational capacity of a model neuron, the Tempotron, which classifies sequences of spikes by linear-threshold operations. We use statistical mechanics and extreme value theory to derive the capacity of the system in random classification tasks. In contrast to its static analog, the Perceptron, the Tempotron's solutions space consists of a large number of small clusters of weight vectors. The capacity of the system per synapse is finite in the large size limit and weakly diverges with the stimulus duration relative to the membrane and synaptic time constants.

4 page, 4 figures, Accepted to Physical Review Letters on 19th Oct. 2010

Cited by in corpus (8)

• Statistical mechanics of complex neural systems and high dimensional data
• Origin of the computational hardness for learning with binary synapses
• Linear Readout of Object Manifolds
• Analog and digital codes in the brain
• Loss shaping enhances exact gradient learning with Eventprop in spiking neural networks
• Linear Classification of Neural Manifolds with Correlated Variability
• Theory and learning protocols for the material tempotron model
• The RL Perceptron: Generalisation Dynamics of Policy Learning in High Dimensions