{"type":"ScholarlyArticle","title":"Similarity-Based Reasoning, Raven's Matrices, and General Intelligence","authors":[{"name":"Can Serif Mekik","slug":"can-serif-mekik","given":"Can Serif","family":"Mekik","affiliation":""},{"name":"Ron Sun","slug":"ron-sun","given":"Ron","family":"Sun","affiliation":""},{"name":"David Yun Dai","slug":"david-yun-dai","given":"David Yun","family":"Dai","affiliation":""}],"abstract":"This paper presents a model tackling a variant of the Raven's Matrices family of human intelligence tests along with computational experiments. Raven's Matrices are thought to challenge human subjects' ability to generalize knowledge and deal with novel situations. We investigate how a generic ability to quickly and accurately generalize knowledge can be succinctly captured by a computational system. This work is distinct from other prominent attempts to deal with the task in terms of adopting a generalized similarity-based approach. Raven's Matrices appear to primarily require similarity-based or analogical reasoning over a set of varied visual stimuli. The similarity-based approach eliminates the need for structure mapping as emphasized in many existing analogical reasoning systems. Instead, it relies on feature-based processing with both relational and non-relational features. Preliminary experimental results suggest that our approach performs comparably to existing symbolic analogy-based models.","doi":"10.24963/ijcai.2018/218","url":"https://ijcai.org/proceedings/2018/218","pdf":"https://ijcai.org/proceedings/2018/0218.pdf","markdown":"https://ijcai.org/proceedings/2018/218.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/218","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Humans and AI","track":"Main track","number":218,"pages":{"first":1576,"last":1582},"keywords":["Humans and AI: Cognitive Systems","Humans and AI: Cognitive Modeling"],"videos":[],"references":[{"position":1,"raw":"[Besold and Schmid, 2016] Tarek R. Besold and Ute Schmid. Why Generality Is Key to Human-Level Artificial Intelligence. Advances in Cognitive Systems, 4:13-24, 2016.","title":"Why Generality Is Key to Human-Level Artificial Intelligence","authors":"R Tarek, Ute Besold, Schmid","year":"2016","venue":"Advances in Cognitive Systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bringsjord and Schimanski, 2003] Selmer Bringsjord and Bettina Schimanski. What is artificial intelligence? Psychometric AI as an answer. In Proceedings of the 18th International Joint Conference on Artificial Intelligence (IJCAI'03), 2003.","title":"What is artificial intelligence? Psychometric AI as an answer","authors":"Schimanski Bringsjord, Selmer Bringsjord, Bettina Schimanski","year":"2003","venue":"Proceedings of the 18th International Joint Conference on Artificial Intelligence (IJCAI'03)","doi":null,"url":null,"internal_url":"/proceedings/2003/127"},{"position":3,"raw":"[Carpenter et al., 1990] Patricia A. Carpenter, Marcel A. Just, and Peter Shell. What One Intelligence Test Measures: A Theoretical Account of the Processing in the Raven Progressive Matrices Test. Psychological Review, 97(3):404-431, 1990.","title":"What One Intelligence Test Measures: A Theoretical Account of the Processing in the Raven Progressive Matrices Test","authors":"Patricia A Carpenter, Marcel A Just, Peter Shell","year":"1990","venue":"Psychological Review","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Feldman, 2016] Jacob Feldman. The simplicity principle in perception and cognition. WIREs Cognitive Science, 7:330-340, 2016.","title":"The simplicity principle in perception and cognition","authors":"Jacob Feldman, Feldman","year":"2016","venue":"WIREs Cognitive Science","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Fowlkes and Mallows, 1983] E. B. Fowlkes and C. L. Mallows. A Method for Comparing Two Hierarchical Clusterings. Journal of the American Statistical Association, 78(383):553-569, 1983.","title":"A Method for Comparing Two Hierarchical Clusterings","authors":"E B Fowlkes, C L Mallows","year":"1983","venue":"Journal of the American Statistical Association","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Gentner and Forbus, 2011] Dedre Gentner and Kenneth Forbus. Computational models of analogy. WIREs Cognitive Science, 2:266-276, 2011.","title":"Computational models of analogy","authors":"Forbus Gentner, Dedre Gentner, Kenneth Forbus","year":"2011","venue":"WIREs Cognitive Science","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Glorot and Bengio, 2010] Xavier Glorot and Yoshua Bengio. Understanding the Difficulty of Training Deep Feedforward Neural Networks. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pages 249-256, 2010.","title":"Understanding the Difficulty of Training Deep Feedforward Neural Networks","authors":"Bengio Glorot, Xavier Glorot, Yoshua Bengio","year":"2010","venue":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hernández-Orallo et al., 2016] José Hernández-Orallo, Fernando Martínez-Plumed, Ute Schmid, Michael Siebers, and David L. Dowe. Computer Models Solving Intelligence Test Problems: Progress and Implications. Artificial Intelligence, 230:74-107, 2016.","title":"Computer Models Solving Intelligence Test Problems: Progress and Implications","authors":"Hernández-Orallo","year":"2016","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hoshen and Werman, 2017] Dokhyam Hoshen and Michael Werman. IQ of Neural Networks. arXiv e-prints, September 2017.","title":"Dokhyam Hoshen and Michael Werman","authors":"Werman Hoshen","year":"2017","venue":"IQ of Neural Networks","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kunda et al., 2013] Maithilee Kunda, Kieth McGreggor, and Ashok K. Goel. A Computational Model for Solving Problems from the Raven's Progressive Matrices Intelligence Test Using Iconic Visual Representations. Cognitive Systems Research, 22-23:47-66, 2013.","title":"A Computational Model for Solving Problems from the Raven's Progressive Matrices Intelligence Test Using Iconic Visual Representations","authors":"Kunda","year":"2013","venue":"Cognitive Systems Research","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Little et al., 2012] Daniel R. Little, Stephan Lewandowsky, and Thomas L. Griffiths. A Bayesian Model of Rule Induction in Raven's Progressive Matrices. In Proceedings of the 34th Annual Conference of the Cognitive Science Society, 2012.","title":"A Bayesian Model of Rule Induction in Raven's Progressive Matrices","authors":"R Daniel, Stephan Little, Thomas L Lewandowsky, Griffiths","year":"2012","venue":"Proceedings of the 34th Annual Conference of the Cognitive Science Society","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Lovett and Forbus, 2017] Andrew Lovett and Kenneth Forbus. Modeling Visual Problem Solving As Analogical Reasoning. Psychological Review, 124(1):60-90, 2017.","title":"Modeling Visual Problem Solving As Analogical Reasoning","authors":"Forbus Lovett, Andrew Lovett, Kenneth Forbus","year":"2017","venue":"Psychological Review","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Matzen et al., 2010] Laura E. Matzen, Zachary O. Benz, Kevin R. Dixon, Jamie Posey, James K. Kroger, and Ann E. Speed. Recreating Raven's: Software for Systematically Generating Large Numbers of Raven-like Matrix Problems with Normed Properties. Behavior Research Methods, 42(2):525-541, 2010.","title":"Recreating Raven's: Software for Systematically Generating Large Numbers of Raven-like Matrix Problems with Normed Properties","authors":"Laura E Matzen, Zachary O Benz, Kevin R Dixon, Jamie Posey, James K Kroger, Ann E Speed","year":"2010","venue":"Behavior Research Methods","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[McGreggor et al., 2014] Kieth McGreggor, Maithilee Kunda, and Ashok Goel. Fractals and Ravens. Artificial Intelligence, 215:1-23, 2014.","title":"Fractals and Ravens","authors":"Kieth Mcgreggor, Maithilee Kunda, Ashok Goel","year":"2014","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Mekik et al., 2017] Can Serif Mekik, Ron Sun, and David Yun Dai. Deep Learning of Raven's Matrices. In Fifth Annual Conference on Advances in Cognitive Systems, 2017.","title":"Deep Learning of Raven's Matrices","authors":"Mekik","year":"2017","venue":"Fifth Annual Conference on Advances in Cognitive Systems","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Nisbett et al., 2012] Richard E. Nisbett, Joshua Aronson, Clancy Blair, William Dickens, James Flynn, Diane F. Halpern, and Eric Turkheimer. Intelligence: New Findings and Theoretical Developments. American Psychologist, 67(2):130-159, 2012.","title":"Intelligence: New Findings and Theoretical Developments","authors":"Richard E Nisbett, Joshua Aronson, Clancy Blair, William Dickens, James Flynn, Diane F Halpern, Eric Turkheimer","year":"2012","venue":"American Psychologist","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Pan and Yang, 2010] Sinno J. Pan and Qiang Yang. A Survey on Transfer Learning. IEEE Transactions on knowledge and data engineering, 22(10):1345-1359, 2010.","title":"A Survey on Transfer Learning","authors":"J Sinno, Qiang Pan, Yang","year":"2010","venue":"IEEE Transactions on knowledge and data engineering","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Penrose and Raven, 1936] Lionel S. Penrose and John C. Raven. A New Series of Perceptual Tests: Preliminary Communication. British Journal of Medical Psychology, 16(2):97-104, 1936.","title":"A New Series of Perceptual Tests: Preliminary Communication","authors":"Lionel S Penrose, John C Raven","year":"1936","venue":"British Journal of Medical Psychology","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Ragni and Neubert, 2014] Marco Ragni and Stefanie Neubert. Analyzing Raven's Intelligence Test: Cognitive Model, Demand and Complexity, In H. Prade and R. Gilles, Eds., Computational Approaches to Analogical Reasoning: Current Trends, Berlin, Heidelberg: Springer-Verlag, 2014.","title":"Analyzing Raven's Intelligence Test: Cognitive Model, Demand and Complexity","authors":"Neubert Ragni, Marco Ragni, Stefanie Neubert","year":"2014","venue":"Computational Approaches to Analogical Reasoning: Current Trends","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Rasmussen and Eliasmith, 2011] Daniel Rasmussen and Chris Eliasmith. A Neural Model of Rule Generation in Inductive Reasoning. Topics in Cognitive Science, 3(1):140-153, January 2011.","title":"A Neural Model of Rule Generation in Inductive Reasoning","authors":"Daniel Rasmussen, Chris Eliasmith","year":"2011","venue":"Topics in Cognitive Science","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Raven, 2008] John Raven. The Raven Progressive Matrices Tests: Their Theoretical Basis and Measurement Model, In J. Raven and C. J. Raven, Eds., Uses and Abuses of Intelligence: Studies Advancing Spearman and Raven's Quest for Non-arbitrary Metrics, pages 17-68, 2008.","title":"The Raven Progressive Matrices Tests: Their Theoretical Basis and Measurement Model","authors":"John Raven","year":"2008","venue":"Uses and Abuses of Intelligence: Studies Advancing Spearman and Raven's Quest for Non-arbitrary Metrics","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Raven et al., 1998a] John Raven, John C. Raven, and J. H. Court. Manual for Raven's Progressive Matrices and Vocabulary Scales: Section 1, General Overview, 1998 Ed. Oxford Psychologists Press, 1998.","title":"Manual for Raven's Progressive Matrices and Vocabulary Scales: Section 1, General Overview","authors":"Raven","year":"1998","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Raven et al., 1998b] John Raven, John C. Raven, and J. H. Court. Manual for Raven's Progressive Matrices and Vocabulary Scales: Section 3, Standard Progressive Matrices, 1998 Ed. Oxford Psychologists Press, 1998.","title":"Manual for Raven's Progressive Matrices and Vocabulary Scales: Section 3, Standard Progressive Matrices","authors":"Raven","year":"1998","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Servan-Schreiber et al., 1991] David Servan-Schreiber, Axel Cleeremans, and James L. McClelland. Graded State Machines: The Representation of Temporal Contingencies in Simple Recurrent Networks. Machine Learning, 7:161-193, 1991.","title":"Graded State Machines: The Representation of Temporal Contingencies in Simple Recurrent Networks","authors":"Servan-Schreiber","year":"1991","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Shore and Johnson, 1980] John E. Shore and Rodney W. Johnson. Axiomatic Derivation of the Principle of Maximum Entropy and the Principle of Minimum Cross- Entropy. IEEE Transactions on Information Theory, 26(1):26-37, 1980.","title":"Axiomatic Derivation of the Principle of Maximum Entropy and the Principle of Minimum Cross-Entropy","authors":"John E Shore, Rodney W Johnson","year":"1980","venue":"IEEE Transactions on Information Theory","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Spearman, 1927] Charles Spearman. The Abilities of Man: Their Nature and Measurement. New York, NY: The MacMillan Company, 1927.","title":"Charles Spearman. The Abilities of Man: Their Nature and Measurement","authors":"Spearman","year":"1927","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Sun, 1994] Ron Sun. Integrating Rules and Connectionism for Robust Commonsense Reasoning. New York: John Wiley & Sons, 1994.","title":"Integrating Rules and Connectionism for Robust Commonsense Reasoning","authors":"Ron Sun","year":"1994","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Sun, 1995] Ron Sun. Robust reasoning: Integrating rule- based and similarity-based reasoning. Artificial Intelligence, 75:241-295, 1995.","title":"Robust reasoning: Integrating rulebased and similarity-based reasoning","authors":"Ron Sun","year":"1995","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Sun, 2016] Ron Sun. Anatomy of the Mind: Exploring Psychological Mechanisms and Processes with the Clarion Cognitive Architecture. New York: Oxford University Press, 2016.","title":"Ron Sun. Anatomy of the Mind: Exploring Psychological Mechanisms and Processes with the Clarion Cognitive Architecture","authors":"Sun","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Turney, 2011] Peter D. Turney. Analogy perception applied to seven tests of word comprehension. Journal of Experimental & Theoretical Artificial Intelligence, 23(3):343-362, 2011.","title":"Analogy perception applied to seven tests of word comprehension","authors":"D Peter, Turney","year":"2011","venue":"Journal of Experimental & Theoretical Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Tversky, 1977] Amos Tversky. Features of Similarity. Psychological Review, 84(4):327-352, 1977.","title":"Amos Tversky. Features of Similarity","authors":"Tversky","year":"1977","venue":"Psychological Review","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zeiler, 2012] Matthew D. Zeiler. ADADELTA: An adaptive learning rate method. arXiv e-prints, 2012.","title":"ADADELTA: An adaptive learning rate method","authors":"D Matthew, Zeiler","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}