AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Inverse Abstraction of Neural Networks Using Symbolic Interpolation

Sumanth Dathathri, Sicun Gao, Richard M. Murray

AAAI 2019 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 7 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
increase nodes per hidden layer (5 to 20)abstraction computation · 2D toyrun-timeHurt
increase number of hidden layers (2 to 4)abstraction computation · 2D toyrun-timeHurt
replace NN controller with controller from overapproximation of {left}cart-pole controller · Cart-polereward: 200.0 -> 200.0No clear effect
verify robustness with both under- and overapproximationsabstractions · 2D toypoints decided: 49 of 50 points decidedImproved
underapproximation threshold 0.3 instead of 0.5 on theta_dotcart-pole abstractions · Cart-poleproperty check: counterexample with -0.31Hurt

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