Search Results for author:
Found 3 papers, 3 papers with code
State-Free Inference of State-Space Models: The Transfer Function Approach
We approach designing a state-space model for deep learning applications through its dual representation, the transfer function, and uncover a highly efficient sequence parallel inference algorithm that is state-free: unlike other proposed algorithms, state-free inference does not incur any significant memory or computational cost with an increase in state size.
Simplified State Space Layers for Sequence Modeling
Models using structured state space sequence (S4) layers have achieved state-of-the-art performance on long-range sequence modeling tasks.
Ranked #3 on
Long-range modeling
on LRA
Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems
The results are a trained SLDS variant that closely approximates the RNN, an auxiliary function that can produce a fixed point for each point in state-space, and a trained nonlinear RNN whose dynamics have been regularized such that its first-order terms perform the computation, if possible.
