A sequential learning algorithm for a spiking neural classifier

• LSNC automatically evolves the architecture.
• Real valued data is encoded using a 2-D encoding having spike amplitude and time.
• Sequential learning algorithm developed for SLSNC.
• Learning algorithm relies on computationally inexpensive operations.

This paper presents a biologically inspired, sequential learning spiking neural classifier (SLSNC) for pattern classification problems. It consists of a two layered neural network and a separate decision block which estimates the predicted class label. Inspired by observations in the neuroscience literature, the input layer employs a new neuron model which converts real valued stimuli into spikes with varying amplitudes and firing times. The intermediate layer neurons are modeled as integrate-and-fire spiking neurons. The decision block identifies that intermediate neuron which fires first and returns the class label associated with that neuron as the predicted class label. The sequential learning algorithm for the spiking neural network automatically determines the network structure from the training samples and adapts its synaptic weights by long term potentiation and long term depression. Performance of SLSNC has been evaluated using a number of benchmark classification problems and the results have been compared with other well-known spiking neural network classifiers in the literature as well as with the standard support vector machine (SVM) with a Gaussian kernel and the fast learning Extreme Learning Machine (ELM) classifiers. The results clearly indicate that the described spiking neural network produces similar or better generalization performance with a smaller network.

Overview of the sequential learning algorithm for a spiking neural classifier. SLSNC consists of a two layered fully connected spiking neural network and a separate decision block. The input layer in the neural network encodes the presented real valued features into spike patterns consisting of varying amplitude and firing times. These spike patterns generated by the input layer neurons is the presynaptic input for the intermediate neurons which are modelled as ‘Integrate-and-Fire’ neurons. The decision block intercepts the output of the intermediate neurons and estimates the predicted class label according to the neuron which fires first. Figure optionsDownload as PowerPoint slide