Visual pattern recognition using unsupervised spike timing dependent plasticity learning

Neuroscience study shows mammalian brain only use millisecond scale time window to process complicated real-life recognition scenarios. However, such speed cannot be achieved by traditional rate-based spiking neural network (SNN). Compared with spiking rate, the specific spiking timing (also called spiking pattern) may convey much more information. In this paper, by using modified rank order coding scheme, the generated absolute analog features have been encoded into the first spike wave with specific spatiotemporal structural information. An intuitive yet powerful feed-forward spiking neural network framework has been proposed, along with its own unsupervised spike-timing-dependent plasticity (STDP) learning rule with dynamic post-synaptic potential threshold. Compared with other state-of-art spiking algorithms, the proposed method uses biologically plausible STDP learning method to learn the selectivity while the dynamic post-synaptic potential threshold guarantees no training sample will be ignored during the learning procedure. Furthermore, unlike the complicated frameworks used in those state-of-art spiking algorithms, the proposed intuitive spiking neural network is not time-consuming and quite capable of on-line learning. A satisfactory experimental result has been achieved on classic MNIST handwritten character database