Johns Hopkins Machine Learning 601.475 Fall 2018
Schedule: Mon/Wed 1:30-2:45pm
Location: Gillman 50
Recitation (optional): Fri 1:30-2:45pm (Hackerman B17)
Instructor: Prof. Mark Dredze


Office hours Location
Monday 11am-12pm: Elliot Schumacher Malone 216
Tuesday 9:45-10:45am: Pamela Shapiro Malone 216
Wednesday 3-4pm: Mark Dredze Malone 339
Thursday 2-3pm: Yuan He Malone 216

Contact email:

Registration
This course is very popular, and interest exceeds space every semester. Therefore, the course has a strict enrollment limit and spots that become available when students drop will be given to students on the waitlist in order. Enrollment is initially restricted to Computer Science and Robotics students only. Students from other departments are able to register after these students have finished registration. Students who cannot register are welcome to attend lectures. Additionally, the course is offered every semester.

Websites for the class



Access to website
"I need login access to the class website."

Complete this form: https://goo.gl/forms/SDHn6cPMcRSTR1Ue2


Description

This course takes an application driven approach to current topics in machine learning. The course covers supervised learning, unsupervised learning, semi-supervised learning, and several other learning settings. We will cover popular algorithms and will focus on how statistical learning algorithms are applied to real world applications. Students will implement several learning algorithms throughout the semester. The goal of this course is to provide students with the basic tools they need to approach various applications, such as:
  • Biology/Bioinformatics
  • Information Retrieval
  • Natural Language Processing
  • Speech Processing
  • Vision
We will focus on fundamental methods applicable to all applications. Application specific techniques, such as feature extraction, will be covered only to the benefit of understanding the basic methods.

Previous Years