Deep neural networks trained through closed-loop optimization to restore normal neural coding patterns in the inferior colliculus can identify novel hearing aid processing strategies that substantially outperform state-of-the-art amplification approaches, achieving 81% restoration of neural activity distortions compared to 7-25% for conventional methods, with performance validated in both in silico simulations and in vivo recordings.

Hearing loss introduces complex distortions in the neural coding of sound that current hearing aids fail to address. Here, we leverage tools for neural control via deep learning to identify novel sound processing strategies to correct these distortions. We use large-scale intracranial recordings from the gerbil inferior colliculus to train deep neural network models of neural coding (ICNets) to serve as in silico surrogates for brains with normal and impaired hearing. We then use the ICNets to train another network (AidNet) to act as an optimal hearing aid, providing the individualized sound processing required to elicit normal neural activity in impaired brains. We find that AidNet outperforms state-of-the-art hearing aid processing by a wide margin in correcting both distortions in neural coding and deficits in simulated phoneme recognition. This successful demonstration of neural restoration via closed-loop optimization opens up new possibilities for improving not only hearing aids, but also other sensory devices and neurotechnologies.