Filters








16,018 Hits in 5.3 sec

Machine Learning and Formal Method (Dagstuhl Seminar 17351)

Sanjit A. Seshia, Zhu, Xianjin (Jerry), Andreas Krause, Susmit Jha, Marc Herbstritt
2018 Dagstuhl Reports  
This report documents the program and the outcomes of Dagstuhl Seminar 17351 "Machine Learning and Formal Methods".  ...  The seminar brought together practitioners and reseachers in machine learning and related areas (such as robotics) with those working in formal methods and related areas (such as programming languages  ...  The classical teaching dimension model, used to describe the sample complexity of learning from helpful teachers, assumes that the learner simply produces any hypothesis consistent with the data provided  ... 
doi:10.4230/dagrep.7.8.55 dblp:journals/dagstuhl-reports/SeshiaZKJ17 fatcat:pw2cuxb3e5eephkw4khs3fnkae

Foreword

John Case, Takeshi Shinohara, Thomas Zeugmann, Sandra Zilles
2008 Theoretical Computer Science  
research in Inductive Inference.  ...  Thus he has been one of the leading contributors in the analysis of robust learning, monotonic learning, the complexity of learning, to name just a few lines of research.  ...  Very prominent classes of formal languages which have been extensively studied in the framework of Inductive Inference from positive data are the class of nonerasing pattern languages and the class of  ... 
doi:10.1016/j.tcs.2008.02.020 fatcat:jftjiljzjbbmbo7uxva4ftfvqa

Development of a Logic Layer in the Semantic Web: Research Issues

Naeem Khalid Janjua, Farookh Khadeer Hussain
2010 2010 Sixth International Conference on Semantics, Knowledge and Grids  
Rules are a means of expressing business processes, policies, contracts etc but most of the studies have focused on the use of monotonic logics in layered development of the semantic web which provides  ...  Adding logic to the web means using rules to make inferences.  ...  Predicate logic and the inferences (deductive logic) we draw from it is an example of monotonic reasoning.  ... 
doi:10.1109/skg.2010.61 dblp:conf/skg/JanjuaH10 fatcat:ln3pql6ftzhmzf4x6uuq232mwm

Foreword

Nicolò Cesa-Bianchi, Rüdiger Reischuk, Thomas Zeugmann
2006 Theoretical Computer Science  
extraction, inductive inference, inductive logic programming, on-line learning as well as to specific algorithmic approaches, e.g., margin-based algorithms, MDL estimation.  ...  The paper by Amano and Maruoka deals with the important class of monotone Boolean functions.  ...  ., the learnability of E-pattern languages from positive data. Classically, this paper also belongs to the area of inductive inference.  ... 
doi:10.1016/j.tcs.2005.10.011 fatcat:hgvr2jkwr5e7tpd2rbi36m3b64

Robust Reasoning for Autonomous Cyber-Physical Systems in Dynamic Environments

Anne Håkansson, Aya Saad, Akhil Anand, Vilde Gjærum, Haakon Robinson, Katrine Seel
2021 Procedia Computer Science  
of cyber-physical systems operating in dynamically changing environments.  ...  This paper presents the assessment of robust reasoning for autonomous cyber-physical systems in dynamic environments.  ...  Acknowledgements This work has been supported by the IDUN-project -NFR 295920 -the Research Council of Norway (RCN).  ... 
doi:10.1016/j.procs.2021.09.171 fatcat:vmrdd4z7yvehdng2qljj7o6rci

A simple calculus for program transformation (inclusive of induction)

Peter Pepper
1987 Science of Computer Programming  
A basic purpose of transformation systems is the application of 'correctness-preserving rules' in order to derive from given programs new,  ...  Although a formal calculus is needed as the basis of such a system, this very fact shall be hidden from the actual user of the resulting system.  ...  consider an instance of stepwise induction that is based on the 'generation principle' of algebraic data types.  ... 
doi:10.1016/0167-6423(87)90008-6 fatcat:z5ayygzxxvfdboitvoid5ccgqm

Case-based representation and learning of pattern languages

Klaus P. Jantke, Steffen Lange
1995 Theoretical Computer Science  
This proves the claim. q Now, we are ready to prove the correctness of S. Since M infers every LEZ(B) from positive data, M, in particular, infers every LE?Z'(BB) on each of its texts.  ...  A couple of learnability results for proper pattern languages are derived both for case-based learning from only positive data and for case-based learning from positive and negative data.  ...  One of them is the most carefully written and detailed referee report we have ever seen.  ... 
doi:10.1016/0304-3975(95)91134-c fatcat:uqtktchsijdltdayludeieuevm

Page 3070 of Mathematical Reviews Vol. , Issue 96e [page]

1996 Mathematical Reviews  
Summary: “Language learnability is investigated in the Gold paradigm of inductive inference from positive data. Angluin gave a characterization of learnable families in this framework.  ...  The paper studies case-based learning of proper pattern languages from only positive data and from positive and negative data. {For the entire collection see MR 95m:68007. } Jerzy W.  ... 

Page 479 of Mathematical Reviews Vol. , Issue 96a [page]

1996 Mathematical Reviews  
We discuss this issue in the framework of inductive inference of length- bounded elementary formal systems (EFSs), which are a kind of logic program over strings of characters and correspond to context  ...  Summary: “We show how to learn in polynomial time monotone d-term DNF formulae (formulae in disjunctive normal form with at most d terms) using positive examples drawn from a distribution that is a generalization  ... 

From positive and intuitionistic bounded arithmetic to monotone proof complexity

Anupam Das
2016 Proceedings of the 31st Annual ACM/IEEE Symposium on Logic in Computer Science - LICS '16  
I would also like to thank Paola Bruscoli, Alessio Guglielmi, Tom Gundersen, Lutz Straßburger and others in the deep inference community for their feedback on early versions of this work.  ...  Acknowledgements I would like to thank Arnold Beckmann for many helpful conversations on this line of research.  ...  of bounded-depth HF systems can be proved in such theories. 2 In this work we identify theories of bounded arithmetic for monotone and deep inference proof systems, via positive and intuitionistic versions  ... 
doi:10.1145/2933575.2934570 dblp:conf/lics/Das16 fatcat:iesm4rgrwfgzdlkxoykayqxslq

Building a Knowledge Base System for an Integration of Logic Programming and Classical Logic [chapter]

Marc Denecker, Joost Vennekens
2008 Lecture Notes in Computer Science  
We report on inference systems that combine state-of-the-art techniques of SAT and ASP. Experiments show that FO(ID) model expansion systems are competitive with the best ASP-solvers.  ...  This paper presents a Knowledge Base project for FO(ID), an extension of classical logic with inductive definitions.  ...  This system supports a rich extension of FO(ID) and, by integrating state-of-the-art technologies from SAT and ASP, it is competitive with the best ASP systems.  ... 
doi:10.1007/978-3-540-89982-2_12 fatcat:t6kp52j4sbcvlckquq5aae53gy

Page 2073 of Mathematical Reviews Vol. , Issue 2003C [page]

2003 Mathematical Reviews  
A framework for unbiased average case comparison of monotone Boolean function inference algorithms is developed using unequal probability sampling.  ...  Therefore, inductive theorem proving constitutes the basis of a suitable formal method for reasoning about data types.  ... 

Integrating Defeasible Argumentation and Machine Learning Techniques [article]

Sergio Alejandro Gomez, Carlos Ivan Chesñevar
2004 arXiv   pre-print
data in order to infer so-called target functions.  ...  Although ML algorithms allow the detection and extraction of interesting patterns of data for several kinds of problems, most of these algorithms are based on quantitative reasoning, as they rely on training  ...  In [IK97] , the authors present a method to generate non-monotonic rules with exceptions from positive/negative examples and background knowledge in Inductive Logic Programming.  ... 
arXiv:cs/0402057v2 fatcat:gcxzssyoa5at3jbo2rgfxa4zqm

Case-based representation and learning of pattern languages [chapter]

Klaus P. Jantke, Steffen Lange
1993 Lecture Notes in Computer Science  
Learning under the standard semantics from positive data is closely related to monotonic language learning.  ...  A couple of learnability results for proper pattern languages are derived both for case-based learning from only positive data and for case-based learning from positive and negative data.  ...  Inductive Pattern Inference Inductive inference is the process of hypothesizing a general rule from eventually incomplete data. It has its origins in the philosophy of science.  ... 
doi:10.1007/3-540-57370-4_39 fatcat:bjytbyuajzemxm7losylplt5mi

Adaptive Logics and the Integration of Induction and Deduction [chapter]

Joke Meheus
2004 Vienna Circle Institute Yearbook  
I moreover illustrate with examples from the sciences that the distinction between induction and deduction is context-dependentan inference treated in one context as deductive may in a different context  ...  The main example concerns Clausius' derivation of Carnot's theorem from an inconsistent set of premises.  ...  In the case of monotonic logics, the formal character of the logic warrants the formal character of the rules. In the case of non-monotonic logics, it does not.  ... 
doi:10.1007/978-1-4020-2196-1_7 fatcat:p2hrjnoi4zborntcx3auk37jna
« Previous Showing results 1 — 15 out of 16,018 results