Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

A Neural Network Solves and Generates Mathematics Problems by Program Synthesis - Paper Explained

Aleksa Gordić - The AI Epiphany via YouTube

Overview

Coursera Spring Sale
40% Off Coursera Plus Annual!
Grab it
Explore a comprehensive analysis of a groundbreaking paper demonstrating how OpenAI's davinci Codex model, combined with prompt engineering, can solve university-level mathematics problems. Delve into the background of OpenAI Codex, examine prompt modification techniques, and witness the model's performance on unseen math courses. Learn about problem generation capabilities, comparing human-generated problems to those created by Codex. Gain insights into quantifying problem statement modification levels and understand the implications of this research for the future of AI in mathematics education and problem-solving.

Syllabus

High level overview of the paper
OpenAI Codex background
Prompt modifications high level
Testing on unseen maths course, problem examples
Prompt modifications in depth
Problem generation: humans vs Codex
Quantifying the problem statement modification levels
Outro

Taught by

Aleksa Gordić - The AI Epiphany

Reviews

Start your review of A Neural Network Solves and Generates Mathematics Problems by Program Synthesis - Paper Explained

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.