Spring 2023 Quantitative Methods: Social Sciences GR5074 section 001

PROJECTS IN ADVANCED MACHINE LEARNING

ADV MACHINE LEARNING

Call Number 12769
Day & Time
Location
T 4:10pm-6:00pm
330 Uris Hall
Points 3
Grading Mode Standard
Approvals Required None
Instructor Michael Parrott
Type SEMINAR
Method of Instruction In-Person
Course Description

Machine learning algorithms continue to advance in their capacity to predict outcomes and rival human judgment in a variety of settings.  This course is designed to offer insight into advanced machine learning models, including Deep Learning, Recurrent Neural Networks, Adversarial Neural Networks, Time Series models and others.  Students are expected to have familiarity with using Python, the scikit-learn package, and github.  The other half of the course will be devoted to students working in key substantive areas, where advanced machine learning will prove helpful -- areas like computer vision and images, text and natural language processing, and tabular data.  Students will be tasked to develop team projects in these areas and they will develop a public portfolio of three (or four) meaningful projects.  By the end of the course, students will be able to show their work by launching their models in live REST APIs and web-applications.

Web Site Vergil
Department Quantitative Methods/Social Sciences
Enrollment 44 students (61 max) as of 10:08AM Thursday, April 25, 2024
Subject Quantitative Methods: Social Sciences
Number GR5074
Section 001
Division Graduate School of Arts and Sciences
Campus Morningside
Note PRIORITY QMSS STUDENTS
Section key 20231QMSS5074G001