Skip to yearly menu bar Skip to main content


FACT: Learning Governing Abstractions Behind Integer Sequences

Peter Belcak · Ard Kastrati · Flavio Schenker · Roger Wattenhofer

Hall J (level 1) #1022

Keywords: [ Evaluation ] [ benchmark ] [ sequences ] [ integer ] [ learning ] [ dataset ] [ abstraction ]


Integer sequences are of central importance to the modeling of concepts admitting complete finitary descriptions. We introduce a novel view on the learning of such concepts and lay down a set of benchmarking tasks aimed at conceptual understanding by machine learning models. These tasks indirectly assess model ability to abstract, and challenge them to reason both interpolatively and extrapolatively from the knowledge gained by observing representative examples. To further aid research in knowledge representation and reasoning, we present FACT, the Finitary Abstraction Comprehension Toolkit. The toolkit surrounds a large dataset of integer sequences comprising both organic and synthetic entries, a library for data pre-processing and generation, a set of model performance evaluation tools, and a collection of baseline model implementations, enabling the making of the future advancements with ease.

Chat is not available.