/mathQ

Data and code for the paper "A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level" by Drori et al., 2022.

Primary LanguagePythonMIT LicenseMIT

A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level

This repository for the paper "A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level" by Drori et al., contains the paper and its supplementary information, data files of all questions, and code for generating all results and figures.

@article{drori2022math,
  author = {Drori, Iddo and Zhang, Sarah and Shuttleworth, Reece and Tang, Leonard and Lu, Albert and Ke, Elizabeth and Liu, Kevin and Chen, Linda and Tran, Sunny and Cheng, Newman and Wang, Roman and Singh, Nikhil and Patti, Taylor L. and Lynch, Jayson and Shporer, Avi and Verma, Nakul and Wu, Eugene and Strang, Gilbert},
  title = {A neural network solves, explains, and generates university math problems by program synthesis and few-shot learning at human level},
  journal = {Proceedings of the National Academy of Sciences (PNAS)},
  volume = {119},
  number = {32},
  year = {2022}
}