, b :: g : h 2. a : d :: e : h 3. a : c :: f : h 4. b : d :: f : h 5. e : f :: g : h 6. c : g :: d : h
, Applying the analogical inference principle to the first proportion a : b :: g : h leads to Bibliography
,
, Case-based reasoning: Foundational issues, methodological variations, and system approaches
, AI communications, vol.7, issue.1, pp.39-59, 1994.
Fast algorithms for mining association rules in large databases ,
, Proc. 20th Int. Conf. on Very Large Data Bases, VLDB'94, pp.487-499, 1994.
Toward the next generation of recommender systems: A survey of the state-of-theart and possible extensions ,
, IEEE Trans. on Knowl. and Data Eng, vol.17, issue.6, pp.734-749, 2005.
By parallel reasoning ,
Analogy and analogical reasoning ,
Optimization Methods for Large-Scale Machine Learning ,
, ArXiv e-prints, 2016.
Learnability and the Vapnik-Chervonenkis dimension ,
, J. ACM, vol.36, issue.4, pp.929-965, 1989.
Lessons from the Netflix prize challenge ,
, SIGKDD Explor. Newsl, vol.9, issue.2, pp.75-79, 2007.
,
, Scalable collaborative filtering with jointly derived neighborhood interpolation weights
, Data Mining, 2007. ICDM'07, pp.43-52, 2007.
,
, Self-testing/correcting with applications to numerical problems
, J. Comput. Syst. Sci, vol.47, issue.3, pp.549-595, 1993.
,
, Applications à l'apprentissage et à la génération
, Proc. Conf. francophone sur l'apprentissage artificiel (CAP), 2009.
Learning by analogy: A classification rule for binary and nominal data ,
, Proc. Inter. Joint Conf. on Artificial Intelligence IJCAI07, pp.678-683, 2007.
Learning a classifier with very few examples: Analogy based and knowledge based generation of new examples for character recognition ,
, Proc. 18th Europ. Conf. on Machine Learning (ECML'07), pp.527-534
, , 2007.
Evaluation of analogical proportions through Kolmogorov complexity ,
, Knowl.-Based Syst, vol.29, pp.20-30, 2012.
Not being at odds with a class: A new way of exploiting neighbors for classification ,
, Proc. 22nd Europ. Conf. on Artificial Intelligence (ECAI'16), vol.285, pp.1662-1663, 2016.
,
, Matching Recommendation Technologies and Domains, pp.367-386
, , 2011.
A tutorial on support vector machines for pattern recognition ,
, Data Mining and Knowledge Discovery, vol.2, pp.121-167, 1998.
Hybrid recommender systems: Survey and experiments ,
, User Modeling and User-Adapted Interaction, vol.12, issue.4, pp.331-370, 2002.
The adaptive web. chapter Hybrid Web Recommender Systems, pp.377-408, 2007. ,
,
, High-level perception, representation, and analogy: A critique of artificial intelligence methodology, Journal of Experimental and Theoretical Artificial Intelligence, vol.4, pp.185-211, 1992.
Nearest neighbor pattern classification ,
DOI : 10.1109/tit.1967.1053964
URL : http://ssg.mit.edu/cal/abs/2000_spring/np_dens/classification/cover67.pdf
, IEEE Transactions on Information Theory, vol.13, pp.21-27, 1967.
Analogy-preserving functions: A way to extend boolean samples ,
URL : https://hal.archives-ouvertes.fr/hal-01668230
, Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, pp.1575-1581, 2017.
Generalizations of Swierczkowski's lemma and the arity gap of finite functions ,
, Discrete Math, vol.309, issue.20, pp.5905-5912, 2009.
,
,
, Actes des 11èmes Journées Françaises de l'Apprentissage, 1996.
Analogy as minimization of description length ,
, Machine Learning and Statistics: The interface, pp.321-336, 1996.
On a quasi-ordering on Boolean functions ,
, Comput. Sci, vol.396, issue.1-3, pp.71-87, 2008.
Training Set Expansion in Handwritten Character Recognition, pp.548-556 ,
, , 2002.
,
, MapReduce: Simplified data processing on large clusters
, Proceedings of the 6th Conference on Symposium on Operating Systems Design & Implementation, vol.6, pp.10-10, 2004.
A logical approach to reasoning by analogy ,
, Proceedings of the 10th International Joint Conference on Artificial Intelligence, vol.1, pp.264-270, 1987.
A heuristic program to solve geometric-analogy problems ,
, Spring Joint Computer Conference, AFIPS'64 (Spring), pp.327-338, 1964.
,
, Constraint-based recommender systems: Technologies and research issues
, Proceedings of the 10th International Conference on Electronic Commerce, ICEC'08, vol.3, pp.1-3, 2008.
The structure-mapping engine: Algorithm and examples, Artificial intelligence, vol.41, issue.1, pp.1-63, 1989. ,
Developing Constraint-based Recommenders, pp.187-215 ,
, , 2011.
A dynamic approach to paradigm-driven analogy ,
, Learning for Natural Language Processing, vol.1040, pp.385-398, 1995.
Structure-mapping: A theoretical framework for analogy ,
, Cognitive Science, vol.7, issue.2, pp.155-170, 1983.
Metaphors and heuristic-driven theory projection (HDTP) ,
, Theoretical Computer Science, vol.354, issue.1, pp.98-117, 2006.
A psychological study of the semantics of animal terms, Journal of Verbal Learning and Verbal Behavior, vol.8, issue.2, pp.176-184, 1969. ,
,
, Proceedings of the Aristotelian Society, vol.60, pp.79-100, 1959.
Models and Analogies in Science, 1966. ,
Evaluating collaborative filtering recommender systems ,
The copycat project: A model of mental fluidity and analogy-making, ACM Trans. Inf. Syst, vol.22, issue.1, pp.5-53, 2004. ,
, Advances in connectionist and neural computation theory, vol.2, pp.29-30, 1994.
Experimenting analogical reasoning in recommendation ,
URL : https://hal.archives-ouvertes.fr/hal-01782596
, Proc. 22nd Int. Symp. on Foundations of Intelligent Systems (ISMIS'15), vol.9384, pp.69-78, 2015.
Analogical classifiers: A theoretical perspective ,
URL : https://hal.archives-ouvertes.fr/hal-01782594
, Proc. 22nd Europ. Conf. on Artificial Intelligence (ECAI'16), pp.689-697, 2016.
Analogy in recommendation. Numerical vs. ordinal: A discussion, 2016 IEEE International Conference on Fuzzy Systems, FUZZ-IEEE 2016, pp.2220-2226, 2016. ,
URL : https://hal.archives-ouvertes.fr/hal-01787372
, Proportions analogiques : créativité et fouille de données
, Rencontres francophones sur la Logique Floue et ses Applications, 2016.
Analogical mapping by constraint satisfaction, Cognitive science, vol.13, issue.3, pp.295-355, 1989. ,
DOI : 10.1016/0364-0213(89)90016-5
URL : http://watarts.uwaterloo.ca/~pthagard/Articles/holyoak.analogical.cogsci.1989.pdf
,
, Surprise, a Python library for recommender systems
Recommender systems: beyond matrix completion, Communications of the ACM, vol.59, issue.11, pp.94-102, 2016. ,
, Advances in Collaborative Filtering, pp.145-186
, , 2011.
Measuring surprise in recommender systems ,
, Procs. of the Workshop on Recommender Systems Evaluation: Dimensions and Design (Workshop Programme of the 8th ACM Conference on Recommender Systems), 2014.
Matrix factorization techniques for recommender systems ,
, Computer, vol.42, issue.8, pp.30-37, 2009.
Analogy and mysticism and the structure of culture (and Comments & Reply) ,
, Current Anthropology, vol.24, issue.2, pp.151-180, 1983.
,
, The BellKor solution to the Netflix grand prize, 2009.
Factor in the neighbors: Scalable and accurate collaborative filtering ,
, ACM Trans. Knowl. Discov. Data, vol.4, issue.1, 2010.
Ordrec: An ordinal model for predicting personalized item rating distributions ,
, Proceedings of the Fifth ACM Conference on Recommender Systems, RecSys'11, pp.117-124, 2011.
, Content-based Recommender Systems: State of the Art and Trends, pp.73-105
, , 2011.
Solving analogies on words: An algorithm ,
DOI : 10.3115/980451.980967
URL : http://dl.acm.org/ft_gateway.cfm?id=980967&type=pdf
, COLING-ACL, pp.728-735, 1998.
,
, De l'analogie rendant compte de la commutation en linguistique
, Habilitation à diriger des recherches, 2003.
One-shot learning of object categories ,
, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.28, issue.4, pp.594-611, 2006.
A structure-mapping model of Raven's progressive matrices, Proceedings of CogSci, vol.10, pp.2761-2766, 2010. ,
,
, Average-case analysis of a nearest neighbor algorithm
, Proceedings of the 13th Int. Joint Conf. on Artificial Intelligence, pp.889-894, 1993.
UCI machine learning repository, 2013. ,
,
, Saussurian analogy: a theoretical account and its application, COLING, pp.717-722, 1996.
,
, Analogical dissimilarity: Definition, algorithms and two experiments in machine learning
, J. Artif. Intell. Res. (JAIR), vol.32, pp.793-824, 2008.
Minimum description length principle applied to structure adaptation for classification under concept drift ,
URL : https://hal.archives-ouvertes.fr/hal-01557212
, 2016 International Joint Conference on Neural Networks, IJCNN 2016, pp.2842-2849, 2016.
Efficient estimation of word representations in vector space, 2013. ,
Relation d'analogie et distance sur un alphabet défini par des traits, IRISA, 2004. ,
,
, Analogy-making as perception: A computer model
Analogy making as a complex adaptive system ,
, In Design Principles for the Immune System and Other Distributed Autonomous Systems, 2001.
Handling analogical proportions in classical logic and fuzzy logics settings ,
, European Conference on Symbolic and Quantitative Approaches to Reasoning and Uncertainty, pp.638-650, 2009.
Being accurate is not enough: how accuracy metrics have hurt recommender systems ,
, Extended Abstracts Proceedings of the 2006 Conference on Human Factors in Computing Systems (CHI'06), pp.1097-1101, 2006.
Linguistic regularities in continuous space word representations ,
, HLT-NAACL, vol.13, pp.746-751, 2013.
An average-case analysis of the k-nearest neighbors classifier for noisy domains ,
, Proceedings of the Fifteenth Int. Joint Conf. on Artificial Intelligence, IJCAI 97, pp.238-245, 1997.
Improving regularized singular value decomposition for collaborative filtering, Proceedings of KDD cup and workshop, pp.5-8, 2007. ,
,
, Essai sur les transformations des opérations logiques: les 256 opérations ternaires de la logique bivalente des propositions
How to Solve It ,
, Induction and analogy in Mathematics, vol.1
Homogeneous logical proportions: Their uniqueness and their role in similaritybased prediction ,
, , 2012.
,
, Analogical proportions and multiple-valued logics
, European Conference on Symbolic and Quantitative Approaches to Reasoning and Uncertainty, pp.497-509, 2013.
From analogical proportion to logical proportions ,
URL : https://hal.archives-ouvertes.fr/hal-01138469
From analogical proportion to logical proportions: A survey ,
, Computational Approaches to Analogical Reasoning: Current Trends, pp.217-244, 2014.
A short introduction to computational trends in analogical reasoning, Computational Approaches to Analogical Reasoning: Current Trends, pp.1-22 ,
,
, Scikit-learn: Machine learning in Python, Journal of Machine Learning Research, vol.12, pp.2825-2830, 2011.
The hidden dimension: a paradigmatic view of data-driven NLP ,
, J. Exp. Theor. Artif. Intell, vol.11, issue.3, pp.391-408, 1999.
A survey on transfer learning ,
, IEEE Trans. on Knowl. and Data Eng, vol.22, issue.10, pp.1345-1359, 2010.
A model for analogical reasoning ,
, Cognitive Psychol, vol.5, pp.1-28, 2005.
Modeling by shortest data description ,
, Automatica, vol.14, issue.5, pp.465-471, 1978.
Problems in Real Analysis: advanced calculus on the real axis ,
, Recommender Systems Handbook
, , 2011.
On essential variables of functions, especially in the algebra of logic ,
, Ann. Acad. Sci. Fenn. Ser. A I. Math, vol.339, pp.3-11, 1963.
,
, Recommendation system with multi-dimensional and parallel-case four-term analogy
, 2011 IEEE International Conference on, pp.3137-3143, 2011.
Scalable similarity-based neighborhood methods with MapReduce ,
, Proceedings of the Sixth ACM Conference on Recommender Systems, RecSys'12, pp.163-170, 2012.
The adaptive web. chapter Collaborative Filtering Recommender Systems, pp.291-324, 2007. ,
,
, Evaluating Recommendation Systems, pp.257-297
, , 2011.
Application of dimensionality reduction in recommender system-a case study, 2000. ,
Probabilistic matrix factorization ,
, Advances in neural information processing systems, pp.1257-1264, 2008.
The theory of representation for Boolean algebras ,
, Trans. of the American Mathematical Society, vol.40, issue.1, pp.37-111, 1936.
,
, An analogical learner for morphological analysis
, Proceedings of the Ninth Conference on Computational Natural Language Learning, pp.120-127, 2005.
,
, Analogical learning and formal proportions: Definitions and methodological issues, 2005.
A theory of the learnable ,
, Commun. ACM, vol.27, issue.11, pp.1134-1142, 1984.
, Statistical Learning Theory
, , 1998.
Essential arities of term operations in finite algebras ,
, Discrete Math, vol.149, issue.1-3, pp.239-259, 1996.
Learning and reasoning by analogy, Communications of the ACM, vol.23, issue.12, pp.689-703, 1980. ,
Regularization through feature knock out ,
DOI : 10.21236/ada454942
URL : http://www.cs.tau.ac.il/~wolf/papers/AIM-2004-025.pdf
On the technique of calculating propositions in symbolic logic ,
, , vol.43, pp.9-28, 1927.
The tabular representation of an analogy between cows and horses, p.11 ,
33 2.2 The six valid patterns of the Boolean proportion (left), and the ten invalid patterns (right) ,
The question mark ? means that sol(a, b, c) is undefined. We can verify that sol(a, b, c) = c ? a + b when the solution is defined, The solutions sol(a, b, c) for every Boolean 3-tuple ,
, Number of unique non-flat proportions in an m-dimensional cube, p.48
The values of AD(a, b, c, d) for 8 patterns of a, b, c, d in B. The 8 remaining patterns are the negated versions of these ,
, AD, p.61
, Accuracies of the 1-NAN, APC and 1-NN algorithms over the Monk datasets, p.73
, Charlie's rating for Titanic is q i t · p u = 1 · 2 + 3 · 1 + 0 · (?1) = 5, p.94
For an item i that u has not rated, the prediction?rprediction? prediction?r ui is set as the solution of the analogical equation 2 : 4 :: 3 :?, i.e. ? r ui = 3 ? 2 + 4 = 5, using the arithmetic proportion, The four users a, b, c, u are in proportion for every item j that they have commonly rated ,
, RMSE and MAE of our clone-based algorithms on the MovieLens-100k and 1M datasets
115 5.5 FCP of our rank prediction algorithm on the MovieLens-100k dataset, p.115 ,
, Two 4-itemsets and their related proportions, with corresponding truth value (A), p.123
The ten best item proportions with a support of more than 200 common ratings, using A ,
8 The ten best item proportions with a support of more than 200 common ratings, using A ,
145 6.3 f is not SAP because f (a) : f (b) :: f (c) : y is not solvable ,
, A geometrical analogy problem: figure A is to figure B as figure C is to which candidate, p.17
, Analogical equation solving process as in [RA05]. The solution is here D 2, p.18
, Analogies between words in the Word2Vect model. Image source
, Snapshot of Copycat during an equation solving process. Image taken from
, The two domains S and T in Cornuéjols' model
, general, U
A(a, b, d 2 , c) and A(a, c, d 3 , b). See also [PR13b], The three equivalence classes: A(a, b, c, d 1 ) ,
, The, vol.36
The 12 non-flat parallelograms in B 3 : the six faces of the cube, and 3 × 2 diagonal parallelograms ,
, A classification problem in B 3. Labels f (x) are on the right cube, p.43
,
,
Class equations are all assumed to be solvable ,
, The analogical dissimilarity AD(a, b, c, d) is equal to the distance ?(d, d ), p.62
Classification process of an extended analogical learner. ? f (x) = f (d ), p.63 ,
, Accuracies (left) of the 1-NAN and 1-NN algorithms over different Boolean functions (m = 8) and training set sizes, with corresponding values of ?, ?, and theoretical accuracy (right). The x axis corresponds to the size of the training set, p.72
Four users a, b, c, u that are in proportion ,
, 107 5.3 Distribution of average support for Spearman's rho (RankAnlg) and MSD (k-NN), p.116
The quality of a proportion is defined as the fraction of component-proportions that stand perfectly ,
The quality of a proportion is defined as the fraction of components that make up perfect proportions, Quality of the 993 proportions ,
135 by three 0, and each 0 is surrounded by three 1. Note that solving any (solvable), A naive application of the analogical inference principle in R 2 ,
Also, we see that we have here a classification problem that is highly non-linearly separable ,
f (b), f (c)) = f (d) ,
A real function f that is piecewise affine ,
Proportion between sets (i) ,
Proportion between sets (ii) ,
Proportion between sets (iii) ,
Boolean proportion (i) ,
Boolean proportion (ii) ,
,
,
,
Analogical dissimilarity for real vectors ,
66 3.10 Quality of the analogical extension ? f ,
,
,
,
,
,