English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

We demonstrate that a neural network pre-trained on text and fine-tuned oncode solves mathematics course problems, explains solutions, and generates newquestions at a human level. We automatically synthesize programs using few-shotlearning and OpenAI's Codex transformer and execute them to solve courseproblems at 81% automatic accuracy. We curate a new dataset of questions fromMIT's largest mathematics courses (Single Variable and Multivariable Calculus,Differential Equations, Introduction to Probability and Statistics, LinearAlgebra, and Mathematics for Computer Science) and Columbia University'sComputational Linear Algebra. We solve questions from a MATH dataset (onPrealgebra, Algebra, Counting and Probability, Intermediate Algebra, NumberTheory, and Precalculus), the latest benchmark of advanced mathematics problemsdesigned to assess mathematical reasoning. We randomly sample questions andgenerate solutions with multiple modalities, including numbers, equations, andplots. The latest GPT-3 language model pre-trained on text automatically solvesonly 18.8% of these university questions using zero-shot learning and 30.8%using few-shot learning and the most recent chain of thought prompting. Incontrast, program synthesis with few-shot learning using Codex fine-tuned oncode generates programs that automatically solve 81% of these questions. Ourapproach improves the previous state-of-the-art automatic solution accuracy onthe benchmark topics from 8.8% to 81.1%. We perform a survey to evaluate thequality and difficulty of generated questions. This work is the first toautomatically solve university-level mathematics course questions at a humanlevel and the first work to explain and generate university-level mathematicscourse questions at scale, a milestone for higher education.

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