Timezone: »

RNNs of RNNs: Recursive Construction of Stable Assemblies of Recurrent Neural Networks
Leo Kozachkov · Michaela Ennis · Jean-Jacques Slotine

Thu Dec 01 02:00 PM -- 04:00 PM (PST) @ Hall J #510

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.

Author Information

Leo Kozachkov (Massachusetts Institute of Technology)
Michaela Ennis (Harvard University)
Jean-Jacques Slotine (Massachusetts Institute of Technology)

More from the Same Authors