Generalisation to unseen topologies: Towards control of biological neural network activity
This work addresses the need for adaptive control in neuroscience applications like activity propagation investigation and treatment of pathologies, but it is incremental as it builds on existing methods.
The paper tackles the problem of controlling activity in biological neural networks with unseen topologies, using a procedurally generated environment and an adjusted transformer-based deep RL agent, which demonstrates generalization from limited training networks to unseen test networks.
Novel imaging and neurostimulation techniques open doors for advancements in closed-loop control of activity in biological neural networks. This would allow for applications in the investigation of activity propagation, and for diagnosis and treatment of pathological behaviour. Due to the partially observable characteristics of activity propagation, through networks in which edges can not be observed, and the dynamic nature of neuronal systems, there is a need for adaptive, generalisable control. In this paper, we introduce an environment that procedurally generates neuronal networks with different topologies to investigate this generalisation problem. Additionally, an existing transformer-based architecture is adjusted to evaluate the generalisation performance of a deep RL agent in the presented partially observable environment. The agent demonstrates the capability to generalise control from a limited number of training networks to unseen test networks.