Solving Abstract Reasoning Tasks with Grammatical Evolution

Author: R. Fischer, M. Jakobs, S. Mücke, K. Morik
Journal: Proceedings of the LWDA 2020
Year: 2020

Citation information

R. Fischer, M. Jakobs, S. Mücke, K. Morik,
Proceedings of the LWDA 2020,
2020,
https://www.researchgate.net/publication/348408303_Solving_Abstract_Reasoning_Tasks_with_Grammatical_Evolution

The Abstraction and Reasoning Corpus (ARC) comprising image-based logical reasoning tasks is intended to serve as a benchmark for measuring intelligence.

Solving these tasks is very difficult for off-the-shelf ML methods due to heterogeneous semantics and low amount of training data.

We here present our approach, which solves tasks via grammatical evolution on a domain-specific language for image transformations.

With this approach, we successfully participated in an online challenge, scoring among the top 4% out of 900 participants.