Delay Embedding Theory of Neural Sequence Models

no code implementations • 17 Jun 2024 • Mitchell Ostrow, Adam Eisen, Ila Fiete

To test whether language models are effectively constructing delay embeddings, we measure the capacities of sequence models to reconstruct unobserved dynamics.

Inductive Bias State Space Models +1

Beyond Geometry: Comparing the Temporal Structure of Computation in Neural Circuits with Dynamical Similarity Analysis

1 code implementation • NeurIPS 2023 • Mitchell Ostrow, Adam Eisen, Leo Kozachkov, Ila Fiete

To bridge this gap, we introduce a novel similarity metric that compares two systems at the level of their dynamics, called Dynamical Similarity Analysis (DSA).