Plis to present "architected interpretability": structured bottlenecks for explainable brain dynamics models
PlisSergey · x · 2026-10-28
Sergey Plis will speak at IMSI on Nov 10 about "architected interpretability" (ArchInterp) for brain dynamics.
- Problem: deep learning predicts diagnostic status from neuroimaging alone, but accurate prediction doesn't explain the underlying brain processes
- Approach: a structured bottleneck between encoder and decoder forces prediction-relevant information through an inspectable, constrainable representation — in their functional neuroimaging work, a graph of brain-region interactions
- Binding the model to this graph ties predictive performance to learned interactions, but establishing whether edges carry biological or causal meaning requires further work
- Related: IMSI workshop "From Connectomics to Brain Dynamics" (Nov 9–13, 2026) on ODE-based brain network modeling, multimodal data, and real-time brain dynamics
Related event: Sergey Plis to Speak on Architected Interpretability for Brain Dynamics(2 posts)→
More from Research
- Real human laughter remains AGI-hard, argue AI improv researchers — korymath · 2026-10-28
- Johns Hopkins lands up to $52M from ARPA-H to build AI that decodes protein misfolding — JosephJacks_ · 2026-10-28
- Microsoft's Diagnostic AI published in Science and open-sourced, retested on Gemini 4 Argon — vivnat · 2026-10-28
- Machenta robot reacts and recovers in real time, trained 100% in simulation — Ed__Johns · 2026-10-28
- DeFM Depth-First Foundation Model: Why Anchor to Depth, Not Estimator Features — chris_j_paxton · 2026-10-28
- AI-powered formal verification finds real Redis/Valkey bugs, incl. a 23-char freeze — LingmingZhang · 2026-10-28