Using transformers to learn extremely fast classifiers taking the form of simple boolean logic functions

“In this work, we introduce Boolformer, the first Transformer architecture trained to perform endto-end symbolic regression of Boolean functions. First, we show that it can predict compact formulas for complex functions which were not seen during training, when provided a clean truth table. Then, we demonstrate its ability to find approximate expressions when provided incomplete and noisy observations.”

I.e. trained transformer model that can convert any binary classification problem having binary input features into a tiny mathematical formula that can then be run near-instantly.

I.e. yo dog, we in here training models so you can train your models.

Beautiful. Finally.

Boolformer: Symbolic Regression of Logic Functions with Transformers

Github