4 papers
NRGPT: An Energy-based Alternative for GPT
Nima Dehmamy, Benjamin Hoover, Bishwajit Saha +3
Generative Pre-trained Transformer (GPT) architectures are the most popular design for language modeling. Energy-based modeling is a different paradigm that views inference as a dy…
Characterizing control between interacting subsystems with deep Jacobian estimation
Adam J. Eisen, Mitchell Ostrow, Sarthak Chandra +3
Biological function arises through the dynamical interactions of multiple subsystems, including those between brain areas, within gene regulatory networks, and more. A common appro…
InputDSA: Demixing then Comparing Recurrent and Externally Driven Dynamics
Ann Huang, Mitchell Ostrow, Satpreet H. Singh +3
In control problems and basic scientific modeling, it is important to compare observations with dynamical simulations. For example, comparing two neural systems can shed light on t…
Contraction Properties of the Global Workspace Primitive
Michaela Ennis, Leo Kozachkov, Jean-Jacques Slotine
To push forward the important emerging research field surrounding multi-area recurrent neural networks (RNNs), we expand theoretically and empirically on the provably stable RNNs o…