A reversibility analysis of encoding methods for spiking neural networks

There is much excitement surrounding the idea of using spiking neural networks (SNNs) as the next generation of function-approximating neural networks. However, with the unique mechanism of communication (neural spikes) between neurons comes the challenge of transferring real-world data into the network to process. Many different encoding methods have been developed for SNNs, most temporal and some spatial. This paper analyzes three of them (Poisson rate encoding, Gaussian receptor fields, and a dual-neuron n-bit representation) and tests to see if the information is fully transformed into the spiking patterns. An oft-neglected consideration in encoding for SNNs is whether or not the real-world data is even truly being introduced to the network. By testing the reversibility of the encoding methods in this paper, the completeness of the information's presence in the pattern of spikes to serve as an input to an SNN is determined.