检索结果-内蒙古大学图书馆

Machine reasoning explainability

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Čyras, Kristijonas Badrinath, Ramamurthy Mohalik, Swarup Kumar Mujumdar, Anusha Nikou, Alexandros Previti, Alessandro Sundararajan, Vaishnavi Feljan, Aneta Vulgarakis Ericsson Research

As a field of AI, Machine Reasoning (MR) uses largely symbolic means to formalize and emulate abstract reasoning. Studies in early MR have notably started inquiries into Explainable AI (XAI) – arguably one of the biggest concerns today for the AI community. Work on explainable MR as well as on MR approaches to explainability in other areas of AI has continued ever since. It is especially potent in modern MR branches, such as argumentation, constraint and logic programming, planning. We hereby aim to provide a selective overview of MR explainability techniques and studies in hopes that insights from this long track of research will complement well the current XAI landscape. This document reports our work in-progress on MR explainability. Copyright © 2020, The Authors. All rights reserved.

关键词： logic programming

Animated logic: Correct Functional Conversion to Conjunctive Normal Form

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Barroso, Pedro Pereira, Mário Ravara, António NOVA LINCS & Departamento de Informática Faculdade de Ciências e Tecnologias da Universidade Nova de Lisboa Portugal

We present an approach to obtain formally verified implementations of classical Computational logic algorithms. We choose the Why3 platform because it allows to implement functions in a style very close to the mathematical definitions, as well as it allows a high degree of automation in the verification process. As proof of concept, we present a mathematical definition of the algorithm to convert propositional formulae to conjunctive normal form, implementations in WhyML (the Why3 language, very similar to OCaml), and proofs of correctness of the implementations. We apply our proposal on two variants of this algorithm: one in direct-style and another with an explicit stack structure. Being both first-order versions, Why3 processes the proofs naturally. Copyright © 2020, The Authors. All rights reserved.

关键词： logic programming

Justifications for goal-directed constraint answer set programming

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Arias, Joaquín Carro, Manuel Chen, Zhuo Gupta, Gopal IMDEA Software Institute Spain Universidad Politécnica de Madrid Spain University of Texas Dallas United States

Ethical and legal concerns make it necessary for programs that may directly influence the life of people (via, e.g., legal or health counseling) to justify in human-understandable terms the advice given. Answer Set programming has a rich semantics that makes it possible to very concisely express complex knowledge. However, justifying why an answer is a consequence from an ASP program may be non-trivial — even more so when the user is an expert in a given domain, but not necessarily knowledgeable in ASP. Most ASP systems generate answers using SAT-solving procedures on ground rules that do not match how humans perceive reasoning. We propose using s(CASP), a query-driven, top-down execution model for predicate ASP with constraints to generate justification trees of (constrained) answer sets. The operational semantics of s(CASP) relies on backward chaining, which is intuitive to follow and lends itself to generating explanations that are easier to translate into natural language. We show how s(CASP) provides minimal justifications for, among others, relevant examples proposed in the literature, both as search trees but, more importantly, as explanations in natural language. We validate our design with real ASP applications and evaluate the cost of generating s(CASP) justification trees. Copyright © 2020, The Authors. All rights reserved.

关键词： logic programming

An application of answer set programming in distributed architectures: ASP microservices

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Costantini, Stefania de Lauretis, Lorenzo Dipartimento di Ingegneria e Scienze dell’Informazione e Matematica Università degli Studi di L’Aquila L’Aquila Italy

We propose an approach to the definition of microservices with an Answer Set programming (ASP) ‘core’, where microservices are a successful abstraction for designing distributed applications as suites of independently deployable interacting components. Such ASP-based components might be employed in distributed architectures related to Cloud Computing or to the Internet of Things (IoT). Copyright © 2020, The Authors. All rights reserved.

关键词： logic programming

Debugging of answer set programs using paracoherent reasoning 34

学校读者我要写书评

暂无评论

Debugging of answer set programs using paracoherent reasonin...

34th Italian Conference on Computational logic, CILC 2019

作者： Cuteri, Bernardo Dodaro, Carmine Ricca, Francesco University of Calabria Italy University of Genoa Italy

Answer Set programming is a well-known declarative programming paradigm proposed in the area of logic programming and non-monotonic reasoning. Although ASP features a simple syntax and an intuitive semantics, errors are common during the development of ASP programs. In this paper we propose a novel debugging approach based on paracoherent reasoning, which allows a user to identify bugs when they are related to wrong constraints. The approach has been implemented in a tool called paradebug, that is made freely available. © 2019 CEUR-WS. All rights reserved.

关键词： logic programming

Declarative approaches to counterfactual explanations for classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Bertossi, Leopoldo Santiago Chile

We propose answer-set programs that specify and compute counterfactual interventions on entities that are input on a classification model. In relation to the outcome of the model, the resulting counterfactual entities serve as a basis for the definition and computation of causality-based explanation scores for the feature values in the entity under classification, namely responsibility scores. The approach and the programs can be applied with black-box models, and also with models that can be specified as logic programs, such as rule-based classifiers. The main focus of this work is on the specification and computation of best counterfactual entities, i.e. those that lead to maximum responsibility scores. From them one can read off the explanations as maximum responsibility feature values in the original entity. We also extend the programs to bring into the picture semantic or domain knowledge. We show how the approach could be extended by means of probabilistic methods, and how the underlying probability distributions could be modified through the use of constraints. Several examples of programs written in the syntax of the DLV ASP-solver, and run with it, are shown. Copyright © 2020, The Authors. All rights reserved.

关键词： logic programming

Exploiting Game Theory for Analysing Justifications

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Marynissen, Simon Bogaerts, Bart Denecker, Marc KU Leuven Vrije Universiteit Brussel

Justification theory is a unifying semantic framework. While it has its roots in non-monotonic logics, it can be applied to various areas in computer science, especially in explainable reasoning;its most central concept is a justification: an explanation why a property holds (or does not hold) in a model. In this paper, we continue the study of justification theory by means of three major contributions. The first is studying the relation between justification theory and game theory. We show that justification frameworks can be seen as a special type of games. The established connection provides the theoretical foundations for our next two contributions. The second contribution is studying under which condition two different dialects of justification theory (graphs as explanations vs trees as explanations) coincide. The third contribution is establishing a precise criterion of when a semantics induced by justification theory yields consistent results. In the past proving that such semantics were consistent took cumbersome and elaborate proofs. We show that these criteria are indeed satisfied for all common semantics of logic programming. This paper is under consideration for acceptance in Theory and Practice of logic programming (TPLP). Copyright © 2020, The Authors. All rights reserved.

关键词： logic programming

Quality management in training companies 3rd

学校读者我要写书评

暂无评论

3rd Conference on Innovation, Engineering and Entrepreneurship, Regional HELIX 2018

作者： Fernandes, Ana Vicente, Henrique Figueiredo, Margarida Ribeiro, Jorge Neves, José Departamento de Química Escola de Ciências E Tecnologia Universidade de Évora Évora Portugal Centro Algoritmi Universidade do Minho Braga Portugal Centro de Investigação em Educação e Psicologia Universidade de Évora Évora Portugal Escola Superior de Tecnologia e Gestão ARC4DigiT – Applied Research Center for Digital Transformation Instituto Politécnico de Viana do Castelo Viana do Castelo Portugal

ISBN: (纸本)9783319913339

This study was carried out in training companies and aims to evaluate customer satisfaction. It focusses at the Organizations’ Quality-of-Management (QoM) that is in itself a major competitive advantage to differentiate them. Indeed, the universe of discourse is set in order to consider not only the complex relationships among the entities that populate it, but also to take into account its inner structure, where incomplete, unknown or even self-contradictory information or knowledge are present. One’s goal is at the development of a comprehensive and integrated computational model to ensure the Organizations’ Performance and its QoM in order to fulfill customer’s requirements. It is based on a logic programming approach to Knowledge Representation and Reasoning and grounded on an Artificial Neural Networks approach to computing. © 2019, Springer International Publishing AG, part of Springer Nature.

关键词： logic programming

An infrastructure for stream reasoning with incremental grounding 34

学校读者我要写书评

暂无评论

An infrastructure for stream reasoning with incremental grou...

34th Italian Conference on Computational logic, CILC 2019

作者： Ianni, Giovambattista Pacenza, Francesco Zangari, Jessica Department of Mathematics and Computer Science University of Calabria Italy

In the context of multiple, repeated, execution of reasoning tasks, typical of stream reasoning and other applicative settings, we propose an incremental reasoning infrastructure, based on the answer set semantics. We focus particularly on the possibility of caching and re-using ground programs, thus knocking down the time necessary for performing this demanding task when it has to be repeated on similar knowledge bases. We present the outline of our incremental caching technique and report about our preliminary experiments. © 2019 CEUR-WS. All rights reserved.

关键词： logic programming