No AI summary available for this article.
Why It Matters
How is computation organized and reused across tasks and time in a trained recurrent network?
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
How is computation organized and reused across tasks and time in a trained recurrent network? Most analyses emphasize the geometry of neural activity, dynamical motifs, or local perturbation growth. We instead study the network's global first-order perturbation response. The finite-horizon Green's operator maps perturbations at each source along a trajectory to their downstream state-space responses and therefore directly represents perturbation routing. Simple reductions of this operator provide task-to-task and time-to-time views of the same computation, while matrix-free products make these...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.40292v1 · Indexed 44 minutes ago