Sergey Plis to Speak on Architected Interpretability for Brain Dynamics

Sergey Plis will speak at IMSI on November 10 about architected interpretability (ArchInterp), an approach using structured bottlenecks to give brain dynamics models inherently testable representations.

2026-10-28 ~ 2026-10-28 · 2 related posts

• Architected Interpretability: Structured Bottlenecks Make Brain-Dynamics Models Causally Explainable — PlisSergey · 2026-10-28

1 near-duplicate retellings: PlisSergey