Abstract
AbstractSymbolic Machine Learning Prover (SMLP) is a tool and a library for system exploration based on data samples obtained by simulating or executing the system on a number of input vectors. SMLP aims at exploring the system based on this data by taking a grey-box approach: SMLP uses symbolic reasoning for ML model exploration and optimization under verification and stability constraints, based on SMT, constraint, and neural network solvers. In addition, the model exploration is guided by probabilistic and statistical methods in a closed feedback loop with the system’s response. SMLP has been applied in industrial setting at Intel for analyzing and optimizing hardware designs at the analog level. SMLP is a general purpose tool and can be applied to any system that can be sampled and modeled by machine learning models.
Publisher
Springer Nature Switzerland
Reference22 articles.
1. Atzmueller, M.: Subgroup discovery. WIREs Data Mining Knowl. Discov. 5(1), 35–49 (2015)
2. Barbosa, H.: cvc5: a versatile and industrial-strength SMT solver. In: TACAS 2022. LNCS, vol. 13243, pp. 415–442. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-99524-9_24
3. Box, G.E.P., Wilson, K.B.: On the experimental attainment of optimum conditions. J. Royal Stat. Soc. Ser. B (Methodological) 13(1), 1–45 (1951)
4. Brauße, F., Khasidashvili, Z., Korovin., K.: Selecting stable safe configurations for systems modelled by neural networks with ReLU activation. In: 2020 Formal Methods in Computer Aided Design, FMCAD 2020, Haifa, Israel, 21–24 September 2020, pp. 119–127. IEEE (2020)
5. Brauße, F., Khasidashvili, Z., Korovin, K.: Combining constraint solving and bayesian techniques for system optimization. In: De Raedt, L. (ed.) Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022, Vienna, Austria, 23–29 July 2022, pp. 1788–1794. ijcai.org (2022)