FACT: Learning Governing Abstractions Behind Integer Sequences
This work addresses the challenge of conceptual understanding in machine learning for integer sequences, which is incremental as it provides tools and benchmarks rather than a breakthrough method.
The paper tackles the problem of learning governing abstractions behind integer sequences by introducing a novel view and benchmarking tasks to assess model ability to abstract and reason. It presents FACT, a toolkit with a dataset, library, evaluation tools, and baseline implementations to aid research in knowledge representation and reasoning.
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.