Depending on the amount of data to process, file generation may take longer.

If it takes too long to generate, you can limit the data by, for example, reducing the range of years.

Chapter

Download BibTeX

Title

Learning to Solve Abstract Reasoning Problems with Neurosymbolic Program Synthesis and Task Generation

Authors

[ 1 ] Instytut Informatyki, Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ P ] employee

Scientific discipline (Law 2.0)

[2.3] Information and communication technology

Year of publication

2024

Chapter type

chapter in monograph

Publication language

english

Keywords
EN
  • Neurosymbolic systems
  • Program synthesis
  • Abstract reasoning
Abstract

EN The ability to think abstractly and reason by analogy is a prerequisite to rapidly adapt to new conditions, tackle newly encountered problems by decomposing them, and synthesize knowledge to solve problems comprehensively. We present TransCoder, a method for solving abstract problems based on neural program synthesis, and conduct a comprehensive analysis of decisions made by the generative module of the proposed architecture. At the core of TransCoder is a typed domain-specific language, designed to facilitate feature engineering and abstract reasoning. In training, we use the programs that failed to solve tasks to generate new tasks and gather them in a synthetic dataset. As each synthetic task created in this way has a known associated program (solution), the model is trained on them in supervised mode. Solutions are represented in a transparent programmatic form, which can be inspected and verified. We demonstrate TransCoder ’s performance using the Abstract Reasoning Corpus dataset, for which our framework generates tens of thousands of synthetic problems with corresponding solutions and facilitates systematic progress in learning.

Pages (from - to)

386 - 402

DOI

10.1007/978-3-031-71167-1_21

URL

https://link.springer.com/chapter/10.1007/978-3-031-71167-1_21

Book

Neural-Symbolic Learning and Reasoning : 18th International Conference, NeSy 2024, Barcelona, Spain, September 9–12, 2024, Proceedings, Part I

Presented on

18th International Conference on Neural-Symbolic Learning and Reasoning NeSy 2024, 9-12.09.2024, Barcelona, Spain

Ministry points / chapter

20

This website uses cookies to remember the authenticated session of the user. For more information, read about Cookies and Privacy Policy.