Depeweg, Stefan ; Rothkopf, Contantin A. ; Jäkel, Frank (2024)
Solving Bongard Problems With a Visual Language and Pragmatic Constraints.
In: Cognitive Science, 48 (5)
doi: 10.1111/cogs.13432
Artikel, Bibliographie
Kurzbeschreibung (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.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2024 |
| Autor(en): | Depeweg, Stefan ; Rothkopf, Contantin A. ; Jäkel, Frank |
| Art des Eintrags: | Bibliographie |
| Titel: | Solving Bongard Problems With a Visual Language and Pragmatic Constraints |
| Sprache: | Englisch |
| Publikationsjahr: | 3 Mai 2024 |
| Verlag: | Wiley Periodicals LLC |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | Cognitive Science |
| Jahrgang/Volume einer Zeitschrift: | 48 |
| (Heft-)Nummer: | 5 |
| DOI: | 10.1111/cogs.13432 |
| Kurzbeschreibung (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. |
| Zusätzliche Informationen: | Art.No.: e13432 |
| Fachbereich(e)/-gebiet(e): | 03 Fachbereich Humanwissenschaften Forschungsfelder Forschungsfelder > Information and Intelligence Forschungsfelder > Information and Intelligence > Cognitive Science Forschungsfelder > Information and Intelligence > Künstliche Intelligenz 03 Fachbereich Humanwissenschaften > Institut für Psychologie 03 Fachbereich Humanwissenschaften > Institut für Psychologie > Modelle höherer Kognition 03 Fachbereich Humanwissenschaften > Institut für Psychologie > Psychologie der Informationsverarbeitung Zentrale Einrichtungen Zentrale Einrichtungen > Centre for Cognitive Science (CCS) Zentrale Einrichtungen > hessian.AI - Hessisches Zentrum für Künstliche Intelligenz |
| Hinterlegungsdatum: | 08 Mai 2024 06:11 |
| Letzte Änderung: | 08 Mai 2024 06:11 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum