stl2vec: Semantic and Interpretable Vector Representation of Temporal Logic

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F24%3A00139091" target="_blank" >RIV/00216224:14330/24:00139091 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.3233/FAIA240638" target="_blank" >http://dx.doi.org/10.3233/FAIA240638</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3233/FAIA240638" target="_blank" >10.3233/FAIA240638</a>

Jazyk výsledku

angličtina

Název v původním jazyce

stl2vec: Semantic and Interpretable Vector Representation of Temporal Logic

Popis výsledku v původním jazyce

Integrating symbolic knowledge and data-driven learning algorithms is a longstanding challenge in Artificial Intelligence. Despite the recognized importance of this task, a notable gap exists due to the discreteness of symbolic representations and the continuous nature of machine-learning computations. One of the desired bridges between these two worlds would be to define semantically grounded vector representation (feature embedding) of logic formulae, thus enabling to perform continuous learning and optimization in the semantic space of formulae. We tackle this goal for knowledge expressed in Signal Temporal Logic (STL) and devise a method to compute continuous embeddings of formulae with several desirable properties: the embedding (i) is finite-dimensional, (ii) faithfully reflects the semantics of the formulae, (iii) does not require any learning but instead is defined from basic principles, (iv) is interpretable. Another significant contribution lies in demonstrating the efficacy of the approach in two tasks: learning model checking, where we predict the probability of requirements being satisfied in stochastic processes; and integrating the embeddings into a neuro-symbolic framework, to constrain the output of a deep-learning generative model to comply to a given logical specification.

Název v anglickém jazyce

stl2vec: Semantic and Interpretable Vector Representation of Temporal Logic

Popis výsledku anglicky

Integrating symbolic knowledge and data-driven learning algorithms is a longstanding challenge in Artificial Intelligence. Despite the recognized importance of this task, a notable gap exists due to the discreteness of symbolic representations and the continuous nature of machine-learning computations. One of the desired bridges between these two worlds would be to define semantically grounded vector representation (feature embedding) of logic formulae, thus enabling to perform continuous learning and optimization in the semantic space of formulae. We tackle this goal for knowledge expressed in Signal Temporal Logic (STL) and devise a method to compute continuous embeddings of formulae with several desirable properties: the embedding (i) is finite-dimensional, (ii) faithfully reflects the semantics of the formulae, (iii) does not require any learning but instead is defined from basic principles, (iv) is interpretable. Another significant contribution lies in demonstrating the efficacy of the approach in two tasks: learning model checking, where we predict the probability of requirements being satisfied in stochastic processes; and integrating the embeddings into a neuro-symbolic framework, to constrain the output of a deep-learning generative model to comply to a given logical specification.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

ECAI 2024, 27th European Conference on Artificial Intelligence

ISBN

9781643685489

ISSN

0922-6389

e-ISSN

—

Počet stran výsledku

8

Strana od-do

1381-1388

Název nakladatele

IOS Press

Místo vydání

Santiago de Compostela, Spain

Místo konání akce

Santiago de Compostela, Spain

Datum konání akce

1. 1. 2024

Typ akce podle státní příslušnosti

CST - Celostátní akce

Kód UT WoS článku

—