A convolutional neural-network framework for modelling auditory sensory cells and synapses

• Published in: Communications biology Vol. 4; no. 1; pp. 827 - 17
• Main Authors: Drakopoulos, Fotios, Baby, Deepak, Verhulst, Sarah
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 01.07.2021; Nature Publishing Group; Nature Portfolio
• Subjects: 631/114/116/2392; 631/114/1305; 631/114/2397; 631/378/2619; 631/553/2695; Biology; Biomedical and Life Sciences; Computational neuroscience; Hearing; Learning algorithms; Life Sciences; Nervous system; Neural networks; Neurons; Neurosciences; Sensory neurons
• ISSN: 2399-3642; 2399-3642
• DOI: 10.1038/s42003-021-02341-5

In classical computational neuroscience, analytical model descriptions are derived from neuronal recordings to mimic the underlying biological system. These neuronal models are typically slow to compute and cannot be integrated within large-scale neuronal simulation frameworks. We present a hybrid, machine-learning and computational-neuroscience approach that transforms analytical models of sensory neurons and synapses into deep-neural-network (DNN) neuronal units with the same biophysical properties. Our DNN-model architecture comprises parallel and differentiable equations that can be used for backpropagation in neuro-engineering applications, and offers a simulation run-time improvement factor of 70 and 280 on CPU or GPU systems respectively. We focussed our development on auditory neurons and synapses, and show that our DNN-model architecture can be extended to a variety of existing analytical models. We describe how our approach for auditory models can be applied to other neuron and synapse types to help accelerate the development of large-scale brain networks and DNN-based treatments of the pathological system. Drakopoulos et al developed a machine-learning and computational-neuroscience approach that transforms analytical models of sensory neurons and synapses into deep-neural-network (DNN) neuronal units with the same biophysical properties. Focusing on auditory neurons and synapses, they showed that their DNN-model architecture could be extended to a variety of existing analytical models and to other neuron and synapse types, thus potentially assisting the development of large-scale brain networks and DNN-based treatments.