Temporal clustering with spiking neurons and dynamic synapses: towards technological applications

We apply spiking neurons with dynamic synapses to detect temporal patterns in a multi-dimensional signal. We use a network of integrate-and-fire neuro ns, fully connected via dynamic synapses, each of which is given by a biolo gically plausible dynamical model based on the exact pre- and post-synaptic spike timing. Dependent on their adaptable configuration (learning) the sy napses automatically implement specific delays. Hence, each output neuron w ith its set of incoming synapses works as a detector for a specific tempora l pattern. The whole network functions as a temporal clustering mechanism w ith one output per input cluster. The classification capability is demonstr ated by illustrative examples including patterns from Poisson processes and the analysis of speech data. (C) 2001 Elsevier Science Ltd. All rights res erved.