AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Safe Partial Diagnosis from Normal Observations

Roni Stern, Brendan Juba

AAAI 2019 · Probabilistic and scientific modeling › Dynamical systems · approach: Latent models of neural activity · 9 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase normal observations from 4 to 4096 with 1 probe (ablation)learned partial model · ISCAS'85 74181detection rate: 0.01 -> 0.75Improved
increase normal observations from 4 to 256 with full probing (ablation)learned partial model · ISCAS'85 74181detection rate: 0.67 -> 1.00Improved
increase number of probes from 1 to 16 at 256 observations (ablation)learned partial model · ISCAS'85 74181detection rate: 0.30 -> 0.72Improved
increase number of probes from 1 to full at 4 observations (ablation)learned partial model · ISCAS'85 74181detection rate: 0.01 -> 0.67Improved
inject more faults (single to triple) with 4 probes (ablation)learned partial model · ISCAS'85 74181fault detection rateImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy