Geometric Methods for Machine Learning
APMTH 220
Subject & Catalog Number
Sign in to Add to Cart
Share
Course Information
Description
Recently, there has been a surge of interest in exploiting geometric structure in data and models in machine learning. This course will give an overview of this emerging research area and its mathematical foundation, with a focus on recent literature and open problems. We will cover a range of topics at the intersection of geometry and machine learning including basic differential geometry, graph representation learning, manifold learning, graph neural networks, machine learning on manifolds, and geometric deep learning. Lectures will be complemented by student-led discussions of relevant papers.
Recommended Prep
Introductory-level knowledge of differential geometry is helpful, but not required.
School
Faculty of Arts & Sciences
Credits
4
Cross Reg
Available for Harvard Cross Registration
Department
Applied Mathematics
Course Component
Lecture
Subject
Applied Mathematics
Grading Basis
FAS Letter Graded
Course Requirements
Pre-Requisite: APMTH 120 and COMPSCI 181
General Education
N/A
Quantitative Reasoning with Data
N/A
Divisional Distribution
Science & Engineering & Applied Science
Course Level
Primarily for Graduate Students
