98,869 Hits in 5.7 sec


2009 Issues in Information Systems  
These are the Military Analogical Reasoning System (MARS) and the Planning for Urban Terrain Operations (PLUTO) system.  ...  This paper describes a group of freely available technologies and tools that the authors have used to develop and field knowledge-based applications.  ...  Figure 2: Military Analogical Reasoning System MARS operates by comparing many instances of stored tactical stories, determining which include analogous situations and thus related lessons learned, and  ... 
doi:10.48009/2_iis_2009_231-236 fatcat:jssmnqgwzfdgfgme55thbgzrve

Instance-based retrieval by analogy

Nicola Fanizzi, Claudia d'Amato, Floriana Esposito
2007 Proceedings of the 2007 ACM symposium on Applied computing - SAC '07  
This work presents a method for retrieval in knowledge bases expressed in Description Logics, founded in the instancebased learning.  ...  The method can be employed both to answer to class-membership queries, even though the answers are not logically entailed by the knowledge base, e.g. there are some inconsistent assertions due to heterogeneous  ...  Acknowledgments This work was partially supported by the regional interest projects DIPIS (Distributed Production as Innovative System) and DDTA (Distretto Digitale Tessile Abbigliamento) in the context  ... 
doi:10.1145/1244002.1244303 dblp:conf/sac/FanizzidE07 fatcat:6di2prexzvgsxnurctheyibriq

From Shallow to Deep Interactions Between Knowledge Representation, Reasoning and Machine Learning (Kay R. Amel group) [article]

Zied Bouraoui and Antoine Cornuéjols and Thierry Denœux and Sébastien Destercke and Didier Dubois and Romain Guillaume and João Marques-Silva and Jérôme Mengin and Henri Prade and Steven Schockaert and Mathieu Serrurier and Christel Vrain
2019 arXiv   pre-print
Then some methodologies combining reasoning and learning are reviewed (such as inductive logic programming, neuro-symbolic reasoning, formal concept analysis, rule-based representations and ML, uncertainty  ...  in ML, or case-based reasoning and analogical reasoning), before discussing examples of synergies between KRR and ML (including topics such as belief functions on regression, EM algorithm versus revision  ...  Case-Based Reasoning, Analogical Reasoning and Transfer Learning Case-based reasoning (CBR for short), e.g., [AP94] is a form of reasoning that exploits data (rather than knowledge) under the form of  ... 
arXiv:1912.06612v1 fatcat:yfnx3pzs6jhxtggaylc76pwjc4

Modular design patterns for hybrid learning and reasoning systems

Michael van Bekkum, Maaike de Boer, Frank van Harmelen, André Meyer-Vitali, Annette ten Teije
2021 Applied intelligence (Boston)  
We are able to describe the architecture of a very large number of hybrid systems by composing only a small set of elementary patterns as building blocks.  ...  organized in a set of elementary patterns and a set of compositional patterns; 3) an application of these design patterns in two realistic use-cases for hybrid AI systems.  ...  This architecture is also used in [53] , where a description logic reasoner is used to come up with a logical justification of classifications produced by a deep learning system.  ... 
doi:10.1007/s10489-021-02394-3 fatcat:ecyruntfdncsbbtdglhllwc6vi

Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases [article]

Michael van Bekkum, Maaike de Boer, Frank van Harmelen, André Meyer-Vitali, Annette ten Teije
2021 arXiv   pre-print
We are able to describe the architecture of a very large number of hybrid systems by composing only a small set of elementary patterns as building blocks.  ...  , organised in a set of elementary patterns and a set of compositional patterns; 3) an application of these design patterns in two realistic use-cases for hybrid AI systems.  ...  Acknowledgement This research was partially funded by the Hybrid Intelligence Center, a 10-year programme funded by the Dutch Ministry of Education, Culture and Science through the Netherlands Organisation  ... 
arXiv:2102.11965v2 fatcat:uo5wj6gw2vc6dhgdrdt26wqslq

A review of the fourth International Workshop on Machine Learning

Rogers P. Hall, Brian Falkenhainer, Nicholas Flann, Steve Hampson, Robert Reinke, Jeff Shrager, Michael H. Sims, Prasad Tadepalli
1987 Machine Learning  
descriptions using symbolic logic.  ...  Traditional approaches to learning logical concept descriptions require finding conditions that define class membership and then classifying an instance precisely within some conceptual class.  ... 
doi:10.1007/bf00114266 fatcat:p3middb4jjcjzdykb5q4orfn6q

Automated support for diagnosis and repair

Dalal Alrajeh, Jeff Kramer, Alessandra Russo, Sebastian Uchitel
2015 Communications of the ACM  
is a reader in applied computational logic in the Pull Quotes The marriage of model checking and logic-based learning thus provides automated support for specification verification, diagnosis, and repair  ...  Machine-learning approaches that are not logic-based have been used in conjunction with theorem proving to find useful premises that help prove a new conjecture based on previously solved mathematical  ...  [14] Model checking and logic-based reasoning are used for program repair; for example, Buccafurri et al.  ... 
doi:10.1145/2658986 fatcat:cmp55coxdjfgzcnksqfwj3hpdu

Non-parametric Statistical Learning Methods for Inductive Classifiers in Semantic Knowledge Bases

Claudia d'Amato, Nicola Fanizzi, Floriana Esposito
2008 2008 IEEE International Conference on Semantic Computing  
We present methods based on epistemic inference that are able to elicit the semantic similarity of individuals in OWL knowledge bases.  ...  This work concerns non-parametric approaches for statistical learning applied to the standard knowledge representations languages adopted in the Semantic Web context.  ...  Reasoning by analogy, similar individuals should likely belong to the extension of similar concepts.  ... 
doi:10.1109/icsc.2008.28 dblp:conf/semco/dAmatoFE08 fatcat:qrtpbglnmjc7jjqbtft47fweq4

Study on Cultivation of Primary Students' Ability to Generate Hypotheses in Science Learning

2018 Advances in Educational Technology and Psychology  
Teachers should help students develop their ability to generate hypotheses through simulating real life situation, making use of materials from daily life suitably and teaching students logical thinking  ...  Doing scientific inquiry is the main way for primary students to learn science. Generating hypotheses is one of the most crucial elements of scientific inquiry.  ...  Acknowledgement This work was Supported by "Capacity Building for Sci-Tech Innovation -Fundamental Scientific Research Funds "(025185305000/201).  ... 
doi:10.23977/aetp.2018.21007 fatcat:odwhcg3eefbmjhkiewrytk7up4

From Reflex to Reflection: Two Tricks AI Could Learn from Us

Jean-Louis Dessalles
2019 Philosophies  
These mechanisms are supposed to operate dynamically and not through pre-processing as in neural networks.  ...  Two directions for qualitative improvement, inspired by comparison with cognitive processes, are proposed here, in the form of two mechanisms: complexity drop and contrast.  ...  By contrast, human children learn new concepts often in one shot, or based on scarce evidence.  ... 
doi:10.3390/philosophies4020027 fatcat:klqpequy75hppfxdmmcx25zmnu

Inferential theory of learning as a conceptual basis for multistrategy learning

Ryszard S. Michalski
1993 Machine Learning  
Such a process is described as a search through a knowledge space, conducted by applying knowledge transformation operators, called knowledge transmutations.  ...  Transmutations can be performed using any type of inference--deduction, induction, or analogy. Several fundamental pairs of transmutations are presented in a novel and very general way.  ...  ., in explanation-based generalization), or analogical (when a more general description is derived by an analogy to some other generalization transformation).  ... 
doi:10.1007/bf00993074 fatcat:dcwpcw2owzdatdmjmmv6pvkrum

Inferential Theory of Learning as a Conceptual Basis for Multistrategy Learning [chapter]

Ryszard S. Michalski
1993 Multistrategy Learning  
V iewing learning as a process of modifying the learner's knowledge by exploring the learner's experience, the theory postulates that any such process can be described as a search in a knowledge space,  ...  To this end, this chapter introduces the Inferential Theory of Learning that provides a conceptual framework for explaining logical capabilities of learning strategies, i.e., their competence.  ...  ., in explanation -based generalization), or analogical (when a more general description is derived by an analogy to some other generalization tran sformation).  ... 
doi:10.1007/978-1-4615-3202-6_2 fatcat:3z4yxkxg3ndunpwth5h4lqmpam

Patterns of Language - A Population Model for Language Structure [article]

Robert John Freeman
1996 arXiv   pre-print
A key problem in the description of language structure is to explain its contradictory properties of specificity and generality, the contrasting poles of formulaic prescription and generative productivity  ...  I argue that this is possible if we accept analogy and similarity as the basic mechanisms of structural definition.  ...  This is the difference between a logical system and a pattern-based, or analogical, system. In a logical system the logical structure specifies the patterns.  ... 
arXiv:cmp-lg/9608004v1 fatcat:ezcpe7cxbfbmfee5bmaotmhnua

Towards integrated neural–symbolic systems for human-level AI: Two research programs helping to bridge the gaps

Tarek R. Besold, Kai-Uwe Kühnberger
2015 Biologically Inspired Cognitive Architectures  
The second program suggests a new approach and computational architecture for the cognitively-inspired anchoring of an agent's learning, knowledge formation, and higher reasoning abilities in real-world  ...  interactions through a closed neural-symbolic acting/sensing-processing-reasoning cycle, potentially providing new foundations for future agent architectures, multi-agent systems, robotics, and cognitive  ...  for their contributions to developing the AAL application scenario sketched in Sect. 6.  ... 
doi:10.1016/j.bica.2015.09.003 fatcat:bwp3ljsconfrzj4lfaazjhbf6u

Explanation-based learning: a survey of programs and perspectives

Thomas Ellman
1989 ACM Computing Surveys  
Explanation-based learning (EBL) is a technique by which an intelligent system can learn by observing examples.  ...  In particular, EBL can be seen as a method that performs four different learning tasks: generalization, chunking, operationalization, and analogy.  ...  This research is surveyed by Angluin and Smith [1983] , Cohen and Feigenbaum [1982], Michalski [1983] , Michalski et al. Fred  ... 
doi:10.1145/66443.66445 fatcat:o25qzli5sza3nczyifhhcl2roi
« Previous Showing results 1 — 15 out of 98,869 results