Filters








18,425 Hits in 6.2 sec

Explanatory machine learning for sequential human teaching [article]

Lun Ai and Johannes Langer and Stephen H. Muggleton and Ute Schmid
2022 arXiv   pre-print
Empirical results show that sequential teaching of concepts with increasing complexity a) has a beneficial effect on human comprehension and b) leads to human re-discovery of divide-and-conquer problem-solving  ...  In this work, we examine the explanatory effects of curriculum order and the presence of machine-learned explanations for sequential problem-solving.  ...  The third author acknowledges support from the UK's EPSRC Human-Like Computing Network.  ... 
arXiv:2205.10250v1 fatcat:3bfy2e7mlfdrxl3vmnhs5iviqe

Beneficial and harmful explanatory machine learning

Lun Ai, Stephen H. Muggleton, Céline Hocquette, Mark Gromowski, Ute Schmid
2021 Machine Learning  
This paper investigates the explanatory effects of a machine learned theory in the context of simple two person games and proposes a framework for identifying the harmfulness of machine explanations based  ...  AbstractGiven the recent successes of Deep Learning in AI there has been increased interest in the role and need for explanations in machine learned theories.  ...  Acknowledgements The contribution of the authors from University of Bamberg is part of a project funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) -405630557 (PainFac-eReader  ... 
doi:10.1007/s10994-020-05941-0 fatcat:4boa2d43zvgg5lhe3k6zoiwzym

Ultra-Strong Machine Learning: comprehensibility of programs learned with ILP

Stephen H. Muggleton, Ute Schmid, Christina Zeller, Alireza Tamaddoni-Nezhad, Tarek Besold
2018 Machine Learning  
We present two sets of experiments testing human comprehensibility of logic programs. In the first experiment we test human comprehensibility with and without predicate invention.  ...  on predictive accuracy, ultimately favouring statistical over symbolic Machine Learning approaches.  ...  learning, that is, on operational effectiveness.  ... 
doi:10.1007/s10994-018-5707-3 fatcat:ka3ppdqnvve2zamzsd2cfxap5a

The Use of an Integrated Tool to Support Teaching and Learning in Artificial Intelligence

T. L. McCluskey, R. M. Simpson
2005 ITALICS  
In this paper we report on a tool called GIPO that has been used for teaching AI students the areas of knowledge acquisition, knowledge engineering, automated planning and machine learning.  ...  We argue that using a high level integrated tool such as GIPO for supporting teaching and learning improves the students' learning experience, and helps integrate the theory and practice in a range of  ...  using machine learning techniques one can potentially avoid the need to hand craft action knowledge 3) the problems and limitations of learning from examples to do with convergence of generalisations,  ... 
doi:10.11120/ital.2005.04030007 fatcat:5ynv6jrxqvfwzfyoqudsjyghtu

Page 377 of Linguistics and Language Behavior Abstracts: LLBA Vol. 25, Issue 1 [page]

1991 Linguistics and Language Behavior Abstracts: LLBA  
Moortgat’s “‘Categorial Investiga- tions: sere and ical Aspects of Lambek Calculus” re- viewed; 91015 machine i!  ...  , formal model; 9101522 expert system, picture series comprehension; 9101514 expert system’s cause-effect oreere capability, Russian cause predicates formalization; 910154 expert systems, reasoning methods  ... 

Exploring the Application of the Random Matrix Thinking Model in Teaching English Predicate Constructions

Pengyuan Liu, Jue Wen, Ning Cao
2022 Mathematical Problems in Engineering  
This paper, the random matrix thinking model, studies the grammatical features of verbs on random matrix and logical relations and designs a model for teaching English predicate constructions by combining  ...  predicate verb compared with the traditional way.  ...  Acknowledgments is work was supported by School of Information and Communication Engineering, Hubei University of Economics.  ... 
doi:10.1155/2022/3865898 fatcat:hmxiv4lhcnb4denifnx722xlza

Merging Virtual World with Data Sciences

Kaleem Razzaq Malik
2017 International Robotics & Automation Journal  
Virtual world is generating large amount of data. Gaming industry is one of the actors in the production of huge amount, variety and velocity of data.  ...  To do so the idea is to bring forth the rich data model known as Resource Description Framework (RDF) of Semantic Web to become a middle source of bridging Big-data and Virtual platforms.  ...  Conflict of interest The author declares no conflict of interest.  ... 
doi:10.15406/iratj.2017.02.00012 fatcat:4innesca75bqvblutpchlnosvq

Relational Restricted Boltzmann Machines: A Probabilistic Logic Learning Approach [chapter]

Navdeep Kaur, Gautam Kunapuli, Tushar Khot, Kristian Kersting, William Cohen, Sriraam Natarajan
2018 Lecture Notes in Computer Science  
We consider the problem of learning Boltzmann machine classifiers from relational data. Our goal is to extend the deep belief framework of RBMs to statistical relational models.  ...  This allows one to exploit the feature hierarchies and the non-linearity inherent in RBMs over the rich representations used in statistical relational learning (SRL).  ...  We focus on discriminative learning, where we learn a conditional distribution of one predicate given all other predicates.  ... 
doi:10.1007/978-3-319-78090-0_7 fatcat:27ssh7u3r5bw7fxmb6ml7l5oti

The Use of the Argument Structure of the Verb in Spanish for Artificial Intelligence: A Proposal

Alfonso Figueroa Colín
2015 Procedia - Social and Behavioral Sciences  
structure of the verb in Spanish to artificial intelligence by employing cognitive computing and machine learning.  ...  In the spirit of the subject of the XXXIII AESLA International Conference, multimodal communication in the 21 st century, this paper offers a modest theoretical approach of the implementation of the predicative  ...  The latter is, rather, the filter that guides the terminology, drives the analysis and, ultimately, governs the project given the final intention of implementing the generated theoretical model on a machine  ... 
doi:10.1016/j.sbspro.2015.11.316 fatcat:ega4iqzffzghlovltaoh3sknae

A Base Camp for Scaling AI [article]

C.J.C. Burges, T. Hart, Z. Yang, S. Cucerzan, R.W. White, A. Pastusiak, J. Lewis
2016 arXiv   pre-print
Modern statistical machine learning (SML) methods share a major limitation with the early approaches to AI: there is no scalable way to adapt them to new domains.  ...  To achieve this, one could attempt to adapt state of the art SML systems to be interpretable and correctable; or one could see how far the simplest possible interpretable, correctable learning methods  ...  This work is the culmination of several years of explorations. We thank Erin Renshaw for her steadfast help with the earlier work.  ... 
arXiv:1612.07896v1 fatcat:7yvyzaanbngjdi66dxpwaw4poq

FINDING TEMPORAL STRUCTURE IN TEXT: MACHINE LEARNING OF SYNTACTIC TEMPORAL RELATIONS

STEVEN BETHARD, JAMES H. MARTIN, SARA KLINGENSTEIN
2007 International Journal of Semantic Computing (IJSC)  
machine translation models with semantics, extracting opinions and the people to which they can be attributed, and learning information extraction models for clinical and biomedical texts.  ...  Teaching Assistant, Blenman Elementary School RESEARCH INTERESTS Natural language processing, information retrieval and machine learning theory and applications, including extracting timelines from unstructured  ...  GRANTS AND FELLOWSHIPS National Science Foundation, "SGER: Relevance Models for Digital Repository Management", $138,213, 2007Management", $138,213, -2008 -Achievement, 1998-2002 Flinn Scholar, 1998  ... 
doi:10.1142/s1793351x07000238 fatcat:m3vci2bgjvgi7oxygeln4h6q4q

Not Deep Learning but Autonomous Learning of Open Innovation for Sustainable Artificial Intelligence

JinHyo Yun, Dooseok Lee, Heungju Ahn, Kyungbae Park, Tan Yigitcanlar
2016 Sustainability  
The core of the interaction model between direct and autonomous learning is the variability of the boundary between proven knowledge and hypothetical knowledge, limitations in knowledge accumulation, as  ...  The key factor of this model is that the process to respond to entries from external environments through interactions between autonomous learning and direct learning as well as to rearrange internal knowledge  ...  The founding sponsors had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, and in the decision to publish the results.  ... 
doi:10.3390/su8080797 fatcat:fjl7o6vrfbfajhl5jvcoi37g5i

Page 13 of Viewpoints in Teaching and Learning Vol. 36, Issue 6 [page]

1960 Viewpoints in Teaching and Learning  
The Effect of Problem-Setting Questions on Rate and Amount an Learning in Programming Teaching Machines @i) A major problem throughout education is the increasing of efficiency and economy in learning.  ...  The development of auto- mated devices for instruction, variously called learning or teaching machines, has been predicated primarily upon their potential contribution toward a solution of this problem  ... 

A multistrategy learning system and its integration into an interactive floorplanning tool [chapter]

Jürgen Herrmann, Reiner Ackermann, Jörg Peters, Detlef Reipa
1994 Lecture Notes in Computer Science  
The presented system COSIMA learns floorplanning rules from structural descriptions incrementally, using a number of cooperating machine learning strategies: Selective inductive generalization generates  ...  most specific, generalizations using predicate weights to select the best one heuristically.  ...  Acknowledgements: We would like to thank Siegfried Bell for useful comments on an earlier version of this paper.  ... 
doi:10.1007/3-540-57868-4_55 fatcat:mroozsbqivdhrlaummcv5whkyu

A Framework for Following Temporal Logic Instructions with Unknown Causal Dependencies [article]

Duo Xu, Faramarz Fekri
2022 arXiv   pre-print
By planning over the product of the symbolic transition model and the automaton derived from the LTL formula, the agent can resolve causal dependencies and break a causally complex problem down into a  ...  Specifically, the symbolic transition model is learned by inductive logic programming (ILP) to capture logic rules of state transitions.  ...  We first use ILP-based method to learn preconditions of symbolic operators. Then with lifted effect sets, we formulate the preconditions and effects of operators as a symbolic transition model.  ... 
arXiv:2204.03196v3 fatcat:7ghjnp6lznaofpnyietqe2nh5a
« Previous Showing results 1 — 15 out of 18,425 results