AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Symbolic Metamodels for Interpreting Black-Boxes Using Primitive Functions

Mahed Abroshan, Saumitra Mishra, Mohammad Mahdi Khalili

AAAI 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Provable post-hoc explanations · 2 citations (OpenAlex)

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
Use SMPF instead of SPSymbolic metamodeling of e^{-3x_0+x_1} · e^{-3x_0+x_1}MSE: 0.009 ± 0.004 -> 0.001±0.0002Improved
Use SMPF instead of SPSymbolic metamodeling of e^{-3x_0+x_1} · e^{-3x_0+x_1}R²: 0.958± 0.014 -> 0.996 ± 0.002Improved
Use SMPF instead of SRSymbolic metamodeling of sin(x_0x_1) · sin(x_0x_1)MSE: 0.0004± 0.0002 -> 0.012± 0.002Hurt
Use SMPF instead of SRSymbolic metamodeling of sin(x_0x_1) · sin(x_0x_1)R²: 0.988± 0.003 -> 0.962 ± 0.004Hurt
Use SMPF instead of SPSymbolic metamodeling of x_0x_1/(x_0²+x_1) · x_0x_1/(x_0²+x_1)R²: 0.878± 0.021 -> 0.895 ± 0.013Improved
Use SMPF instead of SPSymbolic metamodeling of sinc(x_0²+x_1) · sinc(x_0²+x_1)MSE: 0.009 ± 0.002 -> 0.004± 0.0004Improved
Use SMPF instead of SPSymbolic metamodeling of sinc(x_0²+x_1) · sinc(x_0²+x_1)R²: 0.937± 0.015 -> 0.952± 0.003Improved
Use SMPF instead of SPApproximating an MLP black box on Yacht · Yacht test, MLP black boxR² to black box: 0.978 ± 0.016 -> 0.993± 0.003Improved
Use SMPF instead of SPApproximating an SVM black box on Yacht · Yacht test, SVM black boxMSE to black box: 0.014 ± 0.015 -> 0.029 ± 0.013Hurt
Use SMPF instead of SPApproximating an SVM black box on Yacht · Yacht test, SVM black boxR² to black box: 0.974 ± 0.078 -> 0.967 ± 0.120Hurt
Use simpler primitive functions and KST tree search rather than Meijer G-based SMSymbolic metamodeling · e^{-3x_0+x_1}R²: 0.273± 0.019 -> 0.996 ± 0.002Improved

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