[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118340-en":3,"doc-seo-118340-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},118340,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",6,"Technology","SMLP: Symbolic Machine Learning Prover - User Manual","SMLP: Symbolic Machine Learning Prover is an open source tool for exploring and optimizing systems represented by machine learning models. It combines symbolic reasoning with verification and stability constraints using SMT, constraint solvers, and neural network solvers, while guiding exploration through probabilistic and statistical methods. The tool only requires CSV data suitable for ML modeling, typically input/output samples, and supports neural networks, polynomial and tree models. It has been used for analog-level hardware analysis and optimization and is distributed under Apache License v2.0.","arXiv :2405 . 10215v1 [ cs .LG] 16 May 2024  \nSMLP: Symbolic Machine Learning Prover  \n(User Manual)  \nFranz Brauße 1 , Zurab Khasidashvili2 , and Konstantin Korovin3  \n1,3 The University of Manchester, UK  \n2 Intel, Israel  \nMay 17, 2024  \nAbstract  \nSMLP: Symbolic Machine Learning Prover is an open source tool for exploration and optimization of systems represented by machine learning models.1 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.  \nSMLP 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 atthe backend, integration of specialized NN solvers is in progress. Key algorithms behind SMLP are described in detail in [BKK22, BKK20] .  \nSMLP has been developed by Franz Brauße, Zurab Khasidashvili and Konstantin Korovin and is available under the terms of the Apache License v2 .0.2  \nContents  \n1 Introduction 3  \n2 SMLP architecture 4  \n3 How to run SMLP: a quick start 5  \n4 Symbolic representation of the ML model exploration 8  \n5 SMLP problem specification 8  \n6 SMLP input and output 10  \n6.1 SMLP inputs ...................................... 10  \n 6.2 SMLP outputs ..................................... 11  \n1 SMLP is available at: [https://github.com/fbrausse/smlp](https://github.com/fbrausse/smlp)  \n2[https://www.apache.org/licenses/LICENSE-2.0](https://www.apache.org/licenses/LICENSE-2.0)  \n7 Data processing options 11  \n7.1 Data preprocessing options .............................. 11  \n7.1.1 Selecting features for analysis ......................... 11  \n7.1.2 Missing values in responses .......................... 12  \n7.1.3 Constant features ................................ 12  \n7.1.4 Missing values in features ........................... 12  \n7.1.5 Boolean typed features ............................. 12  \n7.1.6 Determining types of responses ........................ 12  \n7.2 Data preparation for analysis ............................. 12  \n7.2.1 Processing categorical features ........................ 13  \n7.2.2 Feature selection for model training ..................... 13  \n7.2.3 Data scaling / normalization ......................... 13  \n7.3 Processing of new data ................................. 14  \n7.4 Output files during data processing .......................... 14  \n8 ML model training and prediction 14  \n8.1 Training ML models .................................. 15  \n8.2 Saving ML models ................................... 15  \n8.3 Rerunning ML models ................................. 16  \n8.4 ML model training and prediction reports ...................... 16  \n9 ML model exploration with SMLP 17  \n9.1 Exploration basic concepts ............................... 18  \n9.2 Mode certify: certification of a stable witness .................... 19  \n9.3 Mode query: querying for a stable witness ...................... 22  \n9.4 Mode verify: assertion verification with stability ................... 23  \n9.5 Mode synthesize: parameter synthesis with stability ................. 27  \n9.6 Mode optimize: multi-objective optimization with stability ............. 29  \n9.7 Mode optsyn: optimized synthesis with stability ................... 30  \n10 Design of experiments 33  \n11 Root cause analysis 36  \n12 Model refinement loop 36  \n1 Introduction  \nSymbolic Machine Learning Prover (SMLP) offers multiple capabilities for system’s design space exploration. These capabilities include methods for selecting which parameters to use in modeling design for configuration optimization and verification; ensuring that the design is robust against environm","cbCaiokWmPg57IiR","https://ap.wps.com/l/cbCaiokWmPg57IiR","pdf",882110,1,39,"English","en",105,"# Introduction\n# SMLP architecture\n# How to run SMLP: a quick start\n# Symbolic representation of the ML model exploration\n# SMLP problem specification\n# SMLP input and output\n## SMLP inputs\n## SMLP outputs\n# Data processing options\n## Data preprocessing options\n## Data preparation for analysis\n# ML model training and prediction\n## Training ML models\n## Saving ML models\n## Rerunning ML models\n## ML model training and prediction reports\n# ML model exploration with SMLP\n## Exploration basic concepts\n## Mode certify\n## Mode query\n## Mode verify\n## Mode synthesize\n## Mode optimize\n## Mode optsyn\n# Design of experiments\n# Root cause analysis\n# Model refinement loop","[{\"question\":\"What is SMLP and what problem does it solve?\",\"answer\":\"SMLP is an open source tool for exploring and optimizing systems represented by ML models. It uses symbolic reasoning to support optimization and verification under stability constraints.\"},{\"question\":\"What kinds of data and model types does SMLP support?\",\"answer\":\"SMLP requires CSV-formatted data suitable for ML modeling, typically system input/output samples. It supports neural networks, polynomial models, and tree models.\"},{\"question\":\"How does SMLP perform model exploration and verification?\",\"answer\":\"SMLP defines stability using a stable witness (a parameter assignment satisfying model constraints). It offers multiple modes such as certify, query, verify, synthesize, optimize, and optsyn, backed by SMT and solver-based reasoning.\"}]","SMLP: Symbolic Machine Learning Prover - User Manual | PDF",1785683168,98,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"smlp-symbolic-machine-learning-prover-user-manual","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/smlp-symbolic-machine-learning-prover-user-manual/118340/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is SMLP and what problem does it solve?","Question",{"text":75,"@type":76},"SMLP is an open source tool for exploring and optimizing systems represented by ML models. It uses symbolic reasoning to support optimization and verification under stability constraints.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What kinds of data and model types does SMLP support?",{"text":80,"@type":76},"SMLP requires CSV-formatted data suitable for ML modeling, typically system input/output samples. It supports neural networks, polynomial models, and tree models.",{"name":82,"@type":73,"acceptedAnswer":83},"How does SMLP perform model exploration and verification?",{"text":84,"@type":76},"SMLP defines stability using a stable witness (a parameter assignment satisfying model constraints). It offers multiple modes such as certify, query, verify, synthesize, optimize, and optsyn, backed by SMT and solver-based reasoning.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,113,118,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]