scientific article; zbMATH DE number 7255073
From MaRDI portal
Publication:4969086
zbMath1498.68153arXiv1909.06588MaRDI QIDQ4969086
Ilker Turkaslan, Rudy Bunel, M. Pawan Kumar, Pushmeet Kohli, Philip H. S. Torr, Jingyue Lu
Publication date: 5 October 2020
Full work available at URL: https://arxiv.org/abs/1909.06588
Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Artificial neural networks and deep learning (68T07) Mixed integer programming (90C11) Specification and verification (program logics, model checking, etc.) (68Q60)
Related Items
\textsf{BDD4BNN}: a BDD-based quantitative analysis framework for binarized neural networks, Exploiting verified neural networks via floating point numerical error, Bisimulations for neural network reduction, Global optimization of objective functions represented by ReLU networks, \textsf{CLEVEREST}: accelerating CEGAR-based neural network verification via adversarial attacks, Neural Network Verification Using Residual Reasoning, Robustness analysis of continuous-depth models with Lagrangian techniques, Fast BATLLNN: Fast Box Analysis of Two-Level Lattice Neural Networks, Boosting robustness verification of semantic feature neighborhoods, Automatic Abstraction Refinement in Neural Network Verification using Sensitivity Analysis, BERN-NN: Tight Bound Propagation For Neural Networks Using Bernstein Polynomial Interval Arithmetic, Improving neural network verification through spurious region guided refinement, Advances in verification of ReLU neural networks
Uses Software
Cites Work
- A hierarchy of relaxations and convex hull characterizations for mixed- integer zero-one programming problems
- Branch-and-bound algorithms: a survey of recent advances in searching, branching, and pruning
- Interval arithmetic
- An Automatic Method for Solving Discrete Programming Problems
- Output Reachable Set Estimation for Switched Linear Systems and Its Application in Safety Verification
- GRASP: a search algorithm for propositional satisfiability
- Splitting on Demand in SAT Modulo Theories
- Strong mixed-integer programming formulations for trained neural networks
