A Machine Learning Framework to Optimize Optic Nerve Electrical Stimulation for Vision Restoration

Abstract

Optic nerve electrical stimulation is a promising technique to restore vision in blind subjects. Selecting effective stimulation protocols is a difficult task. Machine learning methods can be used, but they require a model of the system under stimulation to generate enough training data. Here, we use a convolutional neural network (CNN) as a model of the ventral visual stream. A genetic algorithm drives towards a desired pattern the activation of the units in a hidden layer of the CNN representing a cortical region, by incrementally refining the activation imposed at a previous layer representing the optic nerve. To simulate the pattern of activation elicited by the active sites of an electrode array, a simple point-source model was introduced and its optimization process was investigated for static and dynamic scenes. Psychophysical data confirm that our stimulation evolution framework produces results compatible with natural vision. Machine learning approaches could become a very powerful tool to optimize and personalize neuroprosthetic systems.