AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Bidirectional Inference Networks:A Class of Deep Bayesian Networks for Health Profiling

Hao Wang, Chengzhi Mao, Hao He, Mingmin Zhao, Tommi S. Jaakkola, Dina Katabi

AAAI 2019 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Approximate inference in Bayesian neural networks

Read the paperCheck your idea against 137,217 papers

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
Add composite-likelihood training with iterative inference (CBIN) to BIN (ablation)BIN · SHHS2, V_S={v1,v3}accuracy (%): 75.31 -> 77.16Improved
Add composite-likelihood training with iterative inference (CBIN) to BIN (ablation)BIN · SHHS2, V_S={v4,v5,v6}accuracy (%): 74.36 -> 73.85Hurt
Use prior initialization instead of random initialization for iterative inference (ablation)BIN · SHHS2 arbitrary-subset inferenceaccuracy (%)Improved
Use iterative inference instead of prior-only predictions (ablation)BIN · SHHS2 arbitrary-subset inferenceaccuracy (%)Improved
Add composite-likelihood terms during training (ablation)BIN · Dermatology, V_S={v1}RMSE: 0.0691 -> 0.0643Improved
Add composite-likelihood terms during training (ablation)BIN · Dermatology, V_S={v2}RMSE: 0.1087 -> 0.1062Improved
Train for the iterative inference procedure using CBIN (ablation)BIN · SHHS2 test-time inferenceinference iterationsImproved

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