Filters








102 Hits in 5.0 sec

Characterizing Predicate Arity and Spatial Structure for Inductive Learning of Game Rules [chapter]

Debidatta Dwibedi, Amitabha Mukerjee
2015 Lecture Notes in Computer Science  
Discovered predicate structures and induced rules are demonstrated for several games with varying board layouts and move structures.  ...  Knowledge from spatial structure and semantic graphs is mapped to FOL descriptions of the moves and used in an Inductive Logic framework to infer the valid moves and other rules of the game.  ...  Specifically, we attempt to discover a) the arity and structure of base predicates such as move(), and b) the underlying spatial structure that provides the set of constants that define admissible values  ... 
doi:10.1007/978-3-319-16181-5_23 fatcat:hw3jvndujbbs5i77224c7kp2me

Neuro-Symbolic Hierarchical Rule Induction [article]

Claire Glanois, Xuening Feng, Zhaohui Jiang, Paul Weng, Matthieu Zimmer, Dong Li, Wulong Liu
2021 arXiv   pre-print
In this model, which is built from a set of meta-rules organised in a hierarchical structure, first-order rules are invented by learning embeddings to match facts and body predicates of a meta-rule.  ...  To instantiate it, we specifically design an expressive set of generic meta-rules, and demonstrate they generate a consequent fragment of Horn clauses.  ...  embed some lower-arity predicates as higher-arity proto-rules.  ... 
arXiv:2112.13418v1 fatcat:pebig25vyvg5bl7rmfq2bbnipm

A Theory of Relation Learning and Cross-domain Generalization [article]

Leonidas A. A. Doumas, Guillermo Puebla, Andrea E. Martin, John E. Hummel
2021 arXiv   pre-print
We demonstrate the capacity of the model to learn structured relational representations from a variety of simple visual stimuli, and to perform cross-domain generalization between video games (Breakout  ...  The resulting model learns both the content and format (i.e., structure) of relational representations from non-relational inputs without supervision, when augmented with the capacity for reinforcement  ...  For example, suppose that DORA has learned about spatial relations (e.g., above, rightof, larger) and then learned that when playing the game Breakout-where the goal of the game is to hit a ball with a  ... 
arXiv:1910.05065v5 fatcat:dak3dffaifbanm2kt5f4nx454u

Learning Relational Event Models from Video

Krishna S. R. Dubba, Anthony G. Cohn, David C. Hogg, Mehul Bhatt, Frank Dylla
2015 The Journal of Artificial Intelligence Research  
In this paper, we present a novel framework REMIND (Relational Event Model INDuction) for supervised relational learning of event models from large video datasets using ILP.  ...  Learning event models from this kind of relational spatio-temporal data using relational learning techniques such as Inductive Logic Programming (ILP) hold promise, but have not been successfully applied  ...  Acknowledgements We thank colleagues in the CO-FRIEND, RACE, STRANDS and VIGIL projects consortia for their valuable inputs to this research, and the respective funding from EU Framework 7 (FP7-ICT-214975  ... 
doi:10.1613/jair.4395 fatcat:chaz4bfalfdzbhwaax7642tkli

Concepts Ontology Algebras and Role Descriptions

Cyrus F. Nourani, Patrik Eklund
2017 Position Papers of the 2017 Federated Conference on Computer Science and Information Systems  
Goals are satisfied based on competitive game tree learning. Agent tree computing models are example prototypes for modeling ontology algebras.  ...  A heterogeneous computing model with ontology preserving functions are applied to present concept learning across domains with structural agent morphisms.  ...  Predictive and competitive model learning is presented applying agent game trees. Ontology preservation principles are introduced for learning ontology.  ... 
doi:10.15439/2017f554 dblp:conf/fedcsis/NouraniE17 fatcat:2k23a4lrjvbn5nyquwwmeyvqry

Resolving Relative Time Expressions in Dutch Text with Constraint Handling Rules [chapter]

Matje van de Camp, Henning Christiansen
2013 Lecture Notes in Computer Science  
We present a formal model for natural language semantics using Type Theory with Records (TTR) and argue that it is better suited for representing the meaning of spatial descriptions than traditional formal  ...  Lexical actions in DS are constrained procedures for the incremental projection of compositional semantic structure.  ...  We are thankful to the International Computer Science Institute (University of California at Berkeley) and, in particular, to the people on the Neural Theory of Language project.  ... 
doi:10.1007/978-3-642-41578-4_10 fatcat:rvzj2l4fnvg77aepokghncuhui

Rough Sets and Rough Logic: A KDD Perspective [chapter]

Zdzisław Pawlak, Lech Polkowski, Andrzej Skowron
2000 Studies in Fuzziness and Soft Computing  
The main goal of rough set analysis is induction of approximations of concepts.  ...  The most important issues in this induction process are: -construction of relevant primitive concepts from which approximations of more complex concepts are assembled, -measures of inclusion and similarity  ...  Particular areas of importance for inductive reasoning are Machine Learning, Pattern Recognition and Knowledge Discovery in Data.  ... 
doi:10.1007/978-3-7908-1840-6_13 fatcat:vy35ujzaszcwvevywvjcms4wzy

From information to knowledge

Gerhard Weikum, Martin Theobald
2010 Proceedings of the twenty-ninth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems of data - PODS '10  
Recent endeavors of this kind include DBpedia, EntityCube, KnowItAll, ReadTheWeb, and our own YAGO-NAGA project (and others).  ...  This is enabled by the advent of knowledge-sharing communities such as Wikipedia and the progress in automatically extracting entities and relationships from semistructured as well as natural-language  ...  An overview of approaches for involving humans for quality assurance or active learning, including "wisdom of the crowd" games, is given in [52] .  ... 
doi:10.1145/1807085.1807097 dblp:conf/pods/WeikumT10 fatcat:vtgbi6sjafgsrhmnlztf6q5mxu

A Logical Framework for Imprecise and Conflicting Knowledge Representation for Multi-agent Systems [chapter]

Jair Minoro Abe, Nelio Fernando dos Reis, Cristina Corrêa de Oliveira, Avelino Palma Pimenta
2015 IFIP Advances in Information and Communication Technology  
We discuss one of such system adding suitable modal operators for knowledge.  ...  Nowadays multi-agents has established as one of the most important areas of research and development in information technology.  ...  We define the notion of term as usual. Given a predicate symbol p of arity n and n terms t 1 , …, t n , a basic formula is an expression of the form p(t 1 , …, t n ).  ... 
doi:10.1007/978-3-319-22756-6_25 fatcat:6te76tw46fen5lsenrjbkyokce

On Lions, Impala, and Bigraphs

Steve Benford, Muffy Calder, Tom Rodden, Michele Sevegnani
2016 ACM Transactions on Computer-Human Interaction  
dynamic and spatial behaviour of autonomous agents that interact and move among each other, or within each other.  ...  We present an exploration of modelling an example ubiquitous system, the Savannah game, using the mathematical formalism of bigraphs, which are based on a universal process algebra that encapsulates both  ...  external theories and models of spatial structure.  ... 
doi:10.1145/2882784 fatcat:5awghlyp3fc43iaopql4fzlb3a

Learning and prediction of relational time series

Terence K. Tan, Christian J. Darken
2015 Computational and mathematical organization theory  
Public reporting burden for this collection of information is estimated to average 1 hour per response, including the time for reviewing instruction, searching existing data sources, gathering and maintaining  ...  the data needed, and completing and reviewing the collection of information.  ...  Inductive Logic Programming In inductive learning, also known as concept learning, an agent learns a general function or a set of rules from specific input-output pairs [17] , [18] .  ... 
doi:10.1007/s10588-015-9182-0 fatcat:wooulxv3xjcljdnyjgeijjpmhe

Subject index volumes 1–200

1999 Theoretical Computer Science  
grammars, 1536 grammars, 47 structural equivalence queries, 1428 structural induction problems of P, NP, co-NP and PSPACE, basic -, theorem, 2583 structural membership queries, 1428 structural  ...  algebraic laws, 3432 inference rules for order dependency, 524 sound and complete sets of inference rules, 1167 simple loop check, 1605 sound and complete tableau proof system, 1779 sound and complete  ... 
doi:10.1016/s0304-3975(98)00319-3 fatcat:s22ud3iiqjht7lfbtc3zctk7zm

The declarative imperative

Joseph M. Hellerstein
2010 SIGMOD record  
This juxtaposition raises the possibility that the theory of declarative database query languages can provide a foundation for the next generation of parallel and distributed programming languages.  ...  The rise of multicore processors and cloud computing is putting enormous pressure on the software community to find solutions to the difficulty of parallel and distributed programming.  ...  Syntax and Encapsulation The first frustration programmers have with Datalog is the difficulty of unifying predicates "by eyeball," especially for predicates of high arity.  ... 
doi:10.1145/1860702.1860704 fatcat:p7w5mmjqqjh5pmu2gbmtm24kau

Subject index volumes 101–150

1995 Theoretical Computer Science  
-and continuous 628 discrete-time single-server queueing system 720 discretizations 542 discretized curves, parametrization of - 702 discriminant rules 536 disequality constraints 59 predicates  ...  150, 151 dominant root 73 dominating spaces 630 domination games 512 domineering games 290 snake positions 290 domino snake problems 485 solvability of N 485 Donos 573 Doshita and Yamasaki  ... 
doi:10.1016/0304-3975(95)80002-6 fatcat:azbu2orp7vc75pwux4jxnvxl7m

Changing a Semantics: Opportunism or Courage? [chapter]

Hajnal Andréka, Johan van Benthem, Nick Bezhanishvili, István Németi
2014 Studies in Universal Logic  
The generalized models for higher-order logics introduced by Leon Henkin, and their multiple offspring over the years, have become a standard tool in many areas of logic.  ...  This paper gives a systematic view of generalized model techniques, discusses what they mean in mathematical and philosophical terms, and presents a few technical themes and results about their role in  ...  and in particular, its characteristic nested structures of recursion and inductive reasoning.  ... 
doi:10.1007/978-3-319-09719-0_20 fatcat:vozrx72hn5etnkm3r65t7ejrum
« Previous Showing results 1 — 15 out of 102 results