Biologically-inspired spiking neural networks with Hebbian learning for vision processing

This paper describes our recent efforts to develop biologically-inspired spiking neural network software (called JSpike) for vision processing. The ultimate goal is object recognition with both scale and translational invariance. This paper describes the initial software development effort, including code performance and memory requirement results. The software includes the neural network, image capture code, and graphical display programs. All the software is written in Java. The CPU time requirements for very large networks scale with the number of synapses, but even on a laptop computer billions of synapses can be simulated. While our initial application is image processing, the software is written to be very general and usable for processing other sensor data and for data fusion.