1
|
Depeweg S, Rothkopf CA, Jäkel F. Solving Bongard Problems With a Visual Language and Pragmatic Constraints. Cogn Sci 2024; 48:e13432. [PMID: 38700123 DOI: 10.1111/cogs.13432] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2021] [Revised: 02/15/2024] [Accepted: 02/26/2024] [Indexed: 05/05/2024]
Abstract
More than 50 years ago, Bongard introduced 100 visual concept learning problems as a challenge for artificial vision systems. These problems are now known as Bongard problems. Although they are well known in cognitive science and artificial intelligence, only very little progress has been made toward building systems that can solve a substantial subset of them. In the system presented here, visual features are extracted through image processing and then translated into a symbolic visual vocabulary. We introduce a formal language that allows representing compositional visual concepts based on this vocabulary. Using this language and Bayesian inference, concepts can be induced from the examples that are provided in each problem. We find a reasonable agreement between the concepts with high posterior probability and the solutions formulated by Bongard himself for a subset of 35 problems. While this approach is far from solving Bongard problems like humans, it does considerably better than previous approaches. We discuss the issues we encountered while developing this system and their continuing relevance for understanding visual cognition. For instance, contrary to other concept learning problems, the examples are not random in Bongard problems; instead they are carefully chosen to ensure that the concept can be induced, and we found it helpful to take the resulting pragmatic constraints into account.
Collapse
Affiliation(s)
| | - Contantin A Rothkopf
- Centre for Cognitive Science & Institute of Psychology, Technische Universität Darmstadt
- Frankfurt Institute for Advanced Studies, Frankfurt am Main
| | - Frank Jäkel
- Centre for Cognitive Science & Institute of Psychology, Technische Universität Darmstadt
| |
Collapse
|
2
|
German JS, Jacobs RA. Implications of capacity-limited, generative models for human vision. Behav Brain Sci 2023; 46:e391. [PMID: 38054373 DOI: 10.1017/s0140525x23001772] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/07/2023]
Abstract
Although discriminative deep neural networks are currently dominant in cognitive modeling, we suggest that capacity-limited, generative models are a promising avenue for future work. Generative models tend to learn both local and global features of stimuli and, when properly constrained, can learn componential representations and response biases found in people's behaviors.
Collapse
Affiliation(s)
- Joseph Scott German
- Department of Cognitive Science, University of California, San Diego, La Jolla, CA, USA
| | - Robert A Jacobs
- Department of Brain and Cognitive Sciences, University of Rochester, Rochester, NY, USA https://www2.bcs.rochester.edu/sites/jacobslab/people.html
| |
Collapse
|
3
|
Wichmann FA, Kornblith S, Geirhos R. Neither hype nor gloom do DNNs justice. Behav Brain Sci 2023; 46:e412. [PMID: 38054281 DOI: 10.1017/s0140525x23001711] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/07/2023]
Abstract
Neither the hype exemplified in some exaggerated claims about deep neural networks (DNNs), nor the gloom expressed by Bowers et al. do DNNs as models in vision science justice: DNNs rapidly evolve, and today's limitations are often tomorrow's successes. In addition, providing explanations as well as prediction and image-computability are model desiderata; one should not be favoured at the expense of the other.
Collapse
Affiliation(s)
- Felix A Wichmann
- Neural Information Processing Group, University of Tübingen, Tübingen, Germany
| | | | | |
Collapse
|
4
|
Bowers JS, Malhotra G, Dujmović M, Llera Montero M, Tsvetkov C, Biscione V, Puebla G, Adolfi F, Hummel JE, Heaton RF, Evans BD, Mitchell J, Blything R. Deep problems with neural network models of human vision. Behav Brain Sci 2022; 46:e385. [PMID: 36453586 DOI: 10.1017/s0140525x22002813] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/03/2022]
Abstract
Deep neural networks (DNNs) have had extraordinary successes in classifying photographic images of objects and are often described as the best models of biological vision. This conclusion is largely based on three sets of findings: (1) DNNs are more accurate than any other model in classifying images taken from various datasets, (2) DNNs do the best job in predicting the pattern of human errors in classifying objects taken from various behavioral datasets, and (3) DNNs do the best job in predicting brain signals in response to images taken from various brain datasets (e.g., single cell responses or fMRI data). However, these behavioral and brain datasets do not test hypotheses regarding what features are contributing to good predictions and we show that the predictions may be mediated by DNNs that share little overlap with biological vision. More problematically, we show that DNNs account for almost no results from psychological research. This contradicts the common claim that DNNs are good, let alone the best, models of human object recognition. We argue that theorists interested in developing biologically plausible models of human vision need to direct their attention to explaining psychological findings. More generally, theorists need to build models that explain the results of experiments that manipulate independent variables designed to test hypotheses rather than compete on making the best predictions. We conclude by briefly summarizing various promising modeling approaches that focus on psychological data.
Collapse
Affiliation(s)
- Jeffrey S Bowers
- School of Psychological Science, University of Bristol, Bristol, UK ; https://jeffbowers.blogs.bristol.ac.uk/
| | - Gaurav Malhotra
- School of Psychological Science, University of Bristol, Bristol, UK ; https://jeffbowers.blogs.bristol.ac.uk/
| | - Marin Dujmović
- School of Psychological Science, University of Bristol, Bristol, UK ; https://jeffbowers.blogs.bristol.ac.uk/
| | - Milton Llera Montero
- School of Psychological Science, University of Bristol, Bristol, UK ; https://jeffbowers.blogs.bristol.ac.uk/
| | - Christian Tsvetkov
- School of Psychological Science, University of Bristol, Bristol, UK ; https://jeffbowers.blogs.bristol.ac.uk/
| | - Valerio Biscione
- School of Psychological Science, University of Bristol, Bristol, UK ; https://jeffbowers.blogs.bristol.ac.uk/
| | - Guillermo Puebla
- School of Psychological Science, University of Bristol, Bristol, UK ; https://jeffbowers.blogs.bristol.ac.uk/
| | - Federico Adolfi
- School of Psychological Science, University of Bristol, Bristol, UK ; https://jeffbowers.blogs.bristol.ac.uk/
- Ernst Strüngmann Institute (ESI) for Neuroscience in Cooperation with Max Planck Society, Frankfurt am Main, Germany
| | - John E Hummel
- Department of Psychology, University of Illinois Urbana-Champaign, Champaign, IL, USA
| | - Rachel F Heaton
- Department of Psychology, University of Illinois Urbana-Champaign, Champaign, IL, USA
| | - Benjamin D Evans
- Department of Informatics, School of Engineering and Informatics, University of Sussex, Brighton, UK
| | - Jeffrey Mitchell
- Department of Informatics, School of Engineering and Informatics, University of Sussex, Brighton, UK
| | - Ryan Blything
- School of Psychology, Aston University, Birmingham, UK
| |
Collapse
|
5
|
Heinke D, Leonardis A, Leek EC. What do deep neural networks tell us about biological vision? Vision Res 2022; 198:108069. [PMID: 35561463 DOI: 10.1016/j.visres.2022.108069] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
Affiliation(s)
- Dietmar Heinke
- School of Psychology, University of Birmingham, United Kingdom.
| | - Ales Leonardis
- School of Computer Science, University of Birmingham, United Kingdom
| | - E Charles Leek
- Department of Psychology, University of Liverpool, United Kingdom
| |
Collapse
|
6
|
Biscione V, Bowers JS. Learning online visual invariances for novel objects via supervised and self-supervised training. Neural Netw 2022; 150:222-236. [DOI: 10.1016/j.neunet.2022.02.017] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2021] [Revised: 01/14/2022] [Accepted: 02/23/2022] [Indexed: 10/18/2022]
|