Evaluation of Neuromorphic Spike Encoding of Sound Using Information Theory
This work addresses a gap in evaluating spike encoding methods for audio-based spiking neural networks, though it is incremental as it applies existing information theory to a specific domain.
The authors tackled the lack of systematic evaluation for spike encoding algorithms in sound processing by proposing an information-theoretic framework, finding that Leaky Integrate-and-Fire coding performed best in coding frequency and amplitude with disparities in efficiency among four algorithms.
The problem of spike encoding of sound consists in transforming a sound waveform into spikes. It is of interest in many domains, including the development of audio-based spiking neural networks, where it is the first and most crucial stage of processing. Many algorithms have been proposed to perform spike encoding of sound. However, a systematic approach to quantitatively evaluate their performance is currently lacking. We propose the use of an information-theoretic framework to solve this problem. Specifically, we evaluate the coding efficiency of four spike encoding algorithms on two coding tasks that consist of coding the fundamental characteristics of sound: frequency and amplitude. The algorithms investigated are: Independent Spike Coding, Send-on-Delta coding, Ben's Spiker Algorithm, and Leaky Integrate-and-Fire coding. Using the tools of information theory, we estimate the information that the spikes carry on relevant aspects of an input stimulus. We find disparities in the coding efficiencies of the algorithms, where Leaky Integrate-and-Fire coding performs best. The information-theoretic analysis of their performance on these coding tasks provides insight on the encoding of richer and more complex sound stimuli.