CMSC 472 - Introduction to Deep Learning



Class: TuTh, SHM 2102,

This course is an elementary introduction to a machine learning technique called deep learning, as well as its applications to a variety of domains. Along the way, the course also provides an intuitive introduction to machine learning such as simple models, learning paradigms, optimization, overfitting, importance of data, training caveats, etc. The assignments explore key concepts and simple applications, and the project(s) allows an in-depth exploration of a particular application area. By the end of the course, you will have an overview on the deep learning landscape and its applications. You will also have a working knowledge of several types of neural networks, be able to implement and train them, and have a basic understanding of their inner workings.

Schedule

Exam Dates:


  • Midterm: Thursday, March 12th, in Lecture.
  • Final Exam: Thursday, May 14 10:30 a.m. - 12:30 p.m., Location: TBA

Lectures (Tentative)


Week Starting Tuesday Thursday
01/27 Snow Week (No class)
02/02 Course Introduction
Motivation, Goals, Syllabus,
Assignments Policies
Introduction to Statistical Learning
Simple models
02/09 Simple Models /
Paradigms of learning
Intro to Neural Networks
02/16 Neural Networks II
Neural Networks III
(Forward propagation)
02/23 Neural Networks IV
(Forward propagation,
Labels & Losses)
Neural Networks V
(Softmax Intro, Cross Entropy loss)
03/02 Optimization I
Optimization II
03/09 Optimization III
Midterm
03/16 Spring Break
03/23 Optimization Contd. Back Propagation
03/30 Optimization & Parameter tuning PyTorch tutorial
04/06 Convolutional Neural Networks (CNN) CNN Contd.
04/14 CNN Architectures CNN Architectures Contd.
04/21 Object Detection Object Detection Contd.

Staff

Instructor: Mohammad Nayeem Teli (nayeem at umd.edu)

Office: IRB 2224
Office Hours: M 2 - 3 PM


Teaching Assistants


Name Email (at umd.edu)
Vinayak Gupta vinayakg
Alexander Stein astein0
Matthew Walmer mwalmer
Siddhi Patil scpatil
Gihan Chanaka Jayatilaka gihan


Office Hours

Instructor: M 2:00 - 3:00 PM

Teaching Assistants

Day
Office hours (AVW 4166)
Monday Matt: 11:00 AM - 1:00 PM
Matt: 3:30 PM - 5:30 PM
Tuesday Gihan: 9:00 AM - 11:00 AM
Siddhi: 11:00 AM - 1:00 PM
Alex: 10:00 AM - 2:00 PM
Wednesday Gihan: 11:30 AM - 1:30 PM
Siddhi: 3:30 PM - 5:30 PM
Thursday Vinayak: 10:30 AM - 12:30 PM
Vinayak: 3:30 PM - 5:30 PM,

Please note that a TA may need to leave 5 minutes before the end of the hour in order to go to his/her class. Please be understanding of their schedules.

Class Resources



Previous iterations of this course


Linear algebra material that'll help


Tutorials (libraries and computation resources)


Online Course Tools
  • ELMS - This is where you access homeworks/ assignments, submit them and go to see grades on assignments and to get your class account information.
  • Piazza - This is where you ask questions and discuss.
  • Gradescope - This is where your projects are graded and you submit regrade requests


Assignments (On ELMS)

Homework Due Date*

*All homeworks/assignments are due at 11:59 PM on the due date.