SMLP: Symbolic Machine Learning Prover (User Manual)

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Brauße, Franz, Khasidashvili, Zurab, Korovin, Konstantin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911878841630720
author Brauße, Franz
Khasidashvili, Zurab
Korovin, Konstantin
author_facet Brauße, Franz
Khasidashvili, Zurab
Korovin, Konstantin
contents SMLP: Symbolic Machine Learning Prover an open source tool for exploration and optimization of systems represented by machine learning models. SMLP uses symbolic reasoning for ML model exploration and optimization under verification and stability constraints, based on SMT, constraint and NN solvers. In addition its exploration methods are guided by probabilistic and statistical methods. SMLP is a general purpose tool that requires only data suitable for ML modelling in the csv format (usually samples of the system's input/output). SMLP has been applied at Intel for analyzing and optimizing hardware designs at the analog level. Currently SMLP supports NNs, polynomial and tree models, and uses SMT solvers for reasoning and optimization at the backend, integration of specialized NN solvers is in progress.
format Preprint
id arxiv_https___arxiv_org_abs_2405_10215
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SMLP: Symbolic Machine Learning Prover (User Manual)
Brauße, Franz
Khasidashvili, Zurab
Korovin, Konstantin
Machine Learning
Artificial Intelligence
Logic in Computer Science
Symbolic Computation
Optimization and Control
SMLP: Symbolic Machine Learning Prover an open source tool for exploration and optimization of systems represented by machine learning models. SMLP uses symbolic reasoning for ML model exploration and optimization under verification and stability constraints, based on SMT, constraint and NN solvers. In addition its exploration methods are guided by probabilistic and statistical methods. SMLP is a general purpose tool that requires only data suitable for ML modelling in the csv format (usually samples of the system's input/output). SMLP has been applied at Intel for analyzing and optimizing hardware designs at the analog level. Currently SMLP supports NNs, polynomial and tree models, and uses SMT solvers for reasoning and optimization at the backend, integration of specialized NN solvers is in progress.
title SMLP: Symbolic Machine Learning Prover (User Manual)
topic Machine Learning
Artificial Intelligence
Logic in Computer Science
Symbolic Computation
Optimization and Control
url https://arxiv.org/abs/2405.10215