This course aims to teach learners how to apply deep learning techniques to symbolic mathematics problems. The learning outcomes include understanding how to convert mathematical expressions into trees, generating data for symbolic integration, solving ordinary differential equations, and evaluating models. The course covers topics such as integration by parts, dataset creation, model development, and comparison with traditional mathematical software like Mathematica. The teaching method involves a combination of theoretical explanations, practical examples, and comparisons with existing tools. This course is intended for individuals interested in the intersection of deep learning and symbolic mathematics, particularly those with a background in mathematics or computer science.
Deep Learning for Symbolic Mathematics - Guillaume Lample & Francois Charton
Stanford University via YouTube
Overview
Syllabus
Introduction.
Deep learning for symbolic mathematics.
Starting point.
Basic intuition.
The plan.
From expressions to trees.
Generating data.
Symbolic integration (forward approach).
Symbolic integration (backward approach).
Symbolic integration (integration by parts).
Ordinary Differential Equations (order 1).
Ordinary Differential Equations (ODE) - orde.
Ordinary Differential Equations (order 2).
Datasets.
The model.
Evaluation.
Comparison with Mathematica.
Integration-generalization issues.
Generalization - looking bad.
Generalization - looking better.
Generalization - looking forward.
Generalization - a fun fact.
Inside the beam - Equivalent solutions.
References.
Taught by
Stanford Online
