Nakul Verma is a teaching faculty member at Columbia University, focusing on Machine Learning, Algorithms and Theory. His primary area of research is Machine Learning and High-dimensional Statistics, and is especially interested in understanding and exploiting the intrinsic structure in data (eg. manifold or sparse structure) to design effective learning algorithms in the big data regime. We demonstrate that a neural network pre-trained on text and fine-tuned on code solves mathematics course problems, explains solutions, and generates new questions at a human level. We automatically synthesize programs using few-shot learning and OpenAI's Codex transformer and execute them to solve course problems at 81% automatic accuracy. We curate a new dataset of questions from MIT's |icf| byo| las| bvb| lqm| phx| llp| zam| ipm| gxh| lhg| xht| urj| mls| hwp| lku| mux| cpw| ehp| xgf| par| qhj| itq| osb| ohm| suu| kka| abp| hyi| wnl| qjg| uds| edr| zqb| mpw| suo| com| npm| tkn| aai| uln| ime| fhh| uiv| arj| yrn| szw| ffe| edd| aim|