Optimizing Stimulus Energy for Cochlear Implants with a Machine Learning Model of the Auditory Nerve

TL;DR

This paper develops a machine learning surrogate model, specifically a CNN, to emulate auditory nerve fiber simulations with high accuracy and vastly reduced computation time, enabling efficient optimization of cochlear implant stimuli.

Contribution

A CNN-based surrogate model was created to accurately emulate auditory nerve fiber behavior, significantly speeding up simulations and enabling energy-efficient stimulus optimization.

Findings

CNN achieved R^2 > 0.99 in emulation accuracy

Simulation time reduced by five orders of magnitude

Energy savings of 8% - 45% compared to square wave stimuli

Abstract

Performing simulations with a realistic biophysical auditory nerve fiber model can be very time consuming, due to the complex nature of the calculations involved. Here, a surrogate (approximate) model of such an auditory nerve fiber model was developed using machine learning methods, to perform simulations more efficiently. Several machine learning models were compared, of which a Convolutional Neural Network showed the best performance. In fact, the Convolutional Neural Network was able to emulate the behavior of the auditory nerve fiber model with extremely high similarity ($R^2 > 0.99$), tested under a wide range of experimental conditions, whilst reducing the simulation time by five orders of magnitude. In addition, we introduce a method for randomly generating charge-balanced waveforms using hyperplane projection. In the second part of this paper, the Convolutional Neural Network surrogate model was used by an Evolutionary Algorithm to optimize the shape of the stimulus waveform in terms energy efficiency. The resulting waveforms resemble a positive Gaussian-like peak, preceded by an elongated negative phase. When comparing the energy of the waveforms generated by the Evolutionary Algorithm with the commonly used square wave, energy decreases of 8% - 45% were observed for different pulse durations. These results were validated with the original auditory nerve fiber model, which demonstrates that our proposed surrogate model can be used as its accurate and efficient replacement.