Multilayer feedforward networks are universal approximators
Neural Networks
Neural Networks: A Comprehensive Foundation (3rd Edition)
Neural Networks: A Comprehensive Foundation (3rd Edition)
CAV '08 Proceedings of the 20th international conference on Computer Aided Verification
Bounded model checking of software using SMT solvers instead of SAT solvers
International Journal on Software Tools for Technology Transfer (STTT)
CAV'07 Proceedings of the 19th international conference on Computer aided verification
Applications of Neural Networks in High Assurance Systems
Applications of Neural Networks in High Assurance Systems
Extending CREST with Multiple SMT Solvers and Real Arithmetic
KSE '10 Proceedings of the 2010 Second International Conference on Knowledge and Systems Engineering
A fast linear-arithmetic solver for DPLL(T)
CAV'06 Proceedings of the 18th international conference on Computer Aided Verification
SMT-COMP: satisfiability modulo theories competition
CAV'05 Proceedings of the 17th international conference on Computer Aided Verification
TACAS'06 Proceedings of the 12th international conference on Tools and Algorithms for the Construction and Analysis of Systems
Challenging SMT solvers to verify neural networks
AI Communications - 18th RCRA International Workshop on “Experimental evaluation of algorithms for solving problems with combinatorial explosion”
Hi-index | 0.02 |
In this paper we evaluate state-of-the-art SMT solvers on encodings of verification problems involving Multi-Layer Perceptrons (MLPs), a widely used type of neural network. Verification is a key technology to foster adoption of MLPs in safety-related applications, where stringent requirements about performance and robustness must be ensured and demonstrated. While safety problems for MLPs can be attacked solving Boolean combinations of linear arithmetic constraints, the generated encodings are hard for current state-of-the-art SMT solvers, limiting our ability to verify MLPs in practice.