Functional Connectome: Approximating Brain Networks with Artificial Neural Networks

TL;DR

This paper demonstrates that deep neural networks can effectively approximate biological neural circuits' functions, enabling high-accuracy decoding and generalization in neural systems, with potential applications in neuroscience and reinforcement learning.

Contribution

The study shows that deep learning models can accurately replicate biological neural computations and generalize to new environments, offering a new approach for systems neuroscience research.

Findings

Deep neural networks accurately model synthetic neural circuits.

Networks generalize zero-shot to novel environments.

High accuracy in decoding spatial location.

Abstract

We aimed to explore the capability of deep learning to approximate the function instantiated by biological neural circuits-the functional connectome. Using deep neural networks, we performed supervised learning with firing rate observations drawn from synthetically constructed neural circuits, as well as from an empirically supported Boundary Vector Cell-Place Cell network. The performance of trained networks was quantified using a range of criteria and tasks. Our results show that deep neural networks were able to capture the computations performed by synthetic biological networks with high accuracy, and were highly data efficient and robust to biological plasticity. We show that trained deep neural networks are able to perform zero-shot generalisation in novel environments, and allows for a wealth of tasks such as decoding the animal's location in space with high accuracy. Our study reveals a novel and promising direction in systems neuroscience, and can be expanded upon with a multitude of downstream applications, for example, goal-directed reinforcement learning.