Two Computational Approaches to Visual Analogy: Task‐Specific Models Versus Domain‐General Mapping

Cognitive Science 47 (9):e13347 (2023)
  Copy   BIBTEX


Advances in artificial intelligence have raised a basic question about human intelligence: Is human reasoning best emulated by applying task‐specific knowledge acquired from a wealth of prior experience, or is it based on the domain‐general manipulation and comparison of mental representations? We address this question for the case of visual analogical reasoning. Using realistic images of familiar three‐dimensional objects (cars and their parts), we systematically manipulated viewpoints, part relations, and entity properties in visual analogy problems. We compared human performance to that of two recent deep learning models (Siamese Network and Relation Network) that were directly trained to solve these problems and to apply their task‐specific knowledge to analogical reasoning. We also developed a new model using part‐based comparison (PCM) by applying a domain‐general mapping procedure to learned representations of cars and their component parts. Across four‐term analogies (Experiment 1) and open‐ended analogies (Experiment 2), the domain‐general PCM model, but not the task‐specific deep learning models, generated performance similar in key aspects to that of human reasoners. These findings provide evidence that human‐like analogical reasoning is unlikely to be achieved by applying deep learning with big data to a specific type of analogy problem. Rather, humans do (and machines might) achieve analogical reasoning by learning representations that encode structural information useful for multiple tasks, coupled with efficient computation of relational similarity.



    Upload a copy of this work     Papers currently archived: 92,038

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

Computational modeling of analogy: Destined ever to only be metaphor?Ann Speed - 2008 - Behavioral and Brain Sciences 31 (4):397-398.
Computational Approaches to Comics Analysis.Jochen Laubrock & Alexander Dunst - 2020 - Topics in Cognitive Science 12 (1):274-310.
Analogy.Dedre Gentner - 2017 - In William Bechtel & George Graham (eds.), A Companion to Cognitive Science. Oxford, UK: Blackwell. pp. 107–113.
Precedent and Legal Analogy.Kevin D. Ashley - 2011 - In Colin Aitken, Amalia Amaya, Kevin D. Ashley, Carla Bagnoli, Giorgio Bongiovanni, Bartosz Brożek, Cristiano Castelfranchi, Samuele Chilovi, Marcello Di Bello, Jaap Hage, Kenneth Einar Himma, Lewis A. Kornhauser, Emiliano Lorini, Fabrizio Macagno, Andrei Marmor, J. J. Moreso, Veronica Rodriguez-Blanco, Antonino Rotolo, Giovanni Sartor, Burkhard Schafer, Chiara Valentini, Bart Verheij, Douglas Walton & Wojciech Załuski (eds.), Handbook of Legal Reasoning and Argumentation. Dordrecht, Netherland: Springer Verlag. pp. 673-710.


Added to PP

16 (#908,012)

6 months
10 (#269,579)

Historical graph of downloads
How can I increase my downloads?