RNNs of RNNs: Recursive Construction of Stable Assemblies of Recurrent Neural Networks
This provides a principled approach for understanding distributed, modular brain function, addressing a gap in neuroscience modeling.
The paper tackles the problem of extending recurrent neural network (RNN) theory to multiple interacting brain areas by developing conditions for stable combinations of stable RNNs with massive feedback connections, and shows these stability-constrained networks perform well on challenging sequential-processing benchmarks.
Recurrent neural networks (RNNs) are widely used throughout neuroscience as models of local neural activity. Many properties of single RNNs are well characterized theoretically, but experimental neuroscience has moved in the direction of studying multiple interacting areas, and RNN theory needs to be likewise extended. We take a constructive approach towards this problem, leveraging tools from nonlinear control theory and machine learning to characterize when combinations of stable RNNs will themselves be stable. Importantly, we derive conditions which allow for massive feedback connections between interacting RNNs. We parameterize these conditions for easy optimization using gradient-based techniques, and show that stability-constrained "networks of networks" can perform well on challenging sequential-processing benchmark tasks. Altogether, our results provide a principled approach towards understanding distributed, modular function in the brain.