Supervised Learning in Multilayer Spiking Neural Networks.

In this thesis, a new supervised learning algorithm for multilayer spiking neural networks is presented. Gradient descent learning algorithms have led traditional neural networks with multiple layers to be one of the most powerful and flexible computational models derived from artificial neural networks. However, more recent experimental evidence suggests that biological neural systems use the exact time of single action potentials to encode information. These findings have led to a new way of simulating neural networks based on temporal encoding with single spikes. Analytical demonstrations show that these types of neural networks are computationally more powerful than networks of rate neurons. Conversely, the existing learning algorithms no longer apply to spiking neural networks. Supervised learning algorithms based on gradient descent, such as SpikeProp and its extensions, have been developed for spiking neural networks with multiple layers, but these are limited to a specific model of neurons, with only the first spike being considered. Another learning algorithm, ReSuMe, for single layer networks is based on spike-timing dependent plasticity (STDP) and uses the computational power of multiple spikes; moreover, this algorithm is not limited to a specific neuron model. The algorithm presented here is based on the gradient descent method, while making use of STDP and can be applied to networks with multiple layers. Furthermore, the algorithm is not limited to neurons firing single spikes or specific neuron models. Results on classic benchmarks, such as the XOR problem and the Iris data set, show that the algorithm is capable of non-linear transformations. Complex classification tasks have also been applied with fast convergence times. The results of the simulations show that the new learning rule is as efficient as SpikeProp while having all the advantages of STDP. The supervised learning algorithm for spiking neurons is compared with the back-propagation algorithm for rate neurons by modelling an audio-visual perceptual illusion, the McGurk effect