COMPSCI 682 Neural Networks: A Modern Introduction

This 3-credit course will focus on modern, practical methods for deep learning. The course will begin with a description of simple classifiers such as perceptrons and logistic regression classifiers, and move on to standard neural networks, convolutional neural networks, and some elements of recurrent neural networks, such as long short-term memory networks (LSTMs). The emphasis will be on understanding the basics and on practical application more than on theory. Most applications will be in computer vision, but we will make an effort to cover some natural language processing (NLP) applications as well, contingent upon TA support. The current plan is to use Python and associated packages such as Numpy. Prerequisites include Linear Algebra, Probability and Statistics, and Multivariate Calculus. Assignments will be in Python and potentially some in C++.

THIS COURSE IS FULLY REMOTE AND ASYNCHRONOUS
This semester, unlike normal, this class will be fully remote and asynchronous. That means that there will be no live lectures. “Remote” means that you can access the materials from anywhere (through the course website). “Asynchronous” means that you will be able to access these materials at a variety of different times. (It does not necessarily mean, however, that all materials will be available at all times.) The reason for having this Spring 2022 version of the class remote and asynchnronous is NOT due to COVID, but is instead related to various remote learning and remote teaching goals of the College of Information and Computer Sciences. No matter what happens with COVID, we will continue to teach this class remotely for the duration of the semester. In general, lectures will be available for watching on-line, although not necessarily available for download. In addition, the TA’s and the Professor will offer a variety of live, on-line Zoom sessions to reinforce material and answer questions. More details about the schedule of these sessions will appear later, but our goal will be to provide a variety of options to students to accommodate people in various time zones, and also people with different schedules.

An Important Message From Prof. Learned-Miller

Instructor

Prof. Erik Learned-Miller

Office: CS248
Office hour 1: Friday, 9am-10am EST.
Office hour 2: Friday, 3-pm-4pm EST.

Teaching Assistants

Virat Shejwalkar

TA Hours: Tuesday: 10am-11am EST
Thursday: 9am-10am EST

Ashish Singh

TA Hours: Monday: 4pm-5pm EST
Wednesday: 4pm-5pm EST

Weekly Schedule, Lectures, and Office Hours

1) Every Monday the lectures for the week will be posted. The lectures from the previous week will be taken down at the same time. The justification for this is to make sure students stay up-to-date on the lectures and not procrastinate and watch them all at the same time. In general I will not allow students who miss a lecture to watch them at a later date, just the way a student cannot generally see a live lecture that is missed. If a student wants to review material from a lecture, they will have access to the slides for that lecture, and of course they can take notes while they are watching it.

2) I suggest that the students watch one lecture on Tuesday and one on Thursday . Note that lectures cannot be downloaded to your local machine but they can be watched as many times as the student wants within the week.

3) Each Friday, I will have 2 separate office hours:
- Office hour 1: 9am-10am.
- Office hour 2: 4-pm-5pm.

The main purpose of these office hours is to answer questions about the lectures for that week. I will assume that students have watched the lectures for that week. If you didn't watch the lectures, you are still welcome to show up at the office hours, but the purpose is not to tell you what was in the lecture. It is to clarify concepts that were in the lecture, give new examples, and so on. The office hours are spaced so that most students should be able to attend one or the other. If you cannot attend either, let me know and I will consider changing the time for one of them.
The TA's will also have office hours, as specified on the course web page.

Accommodation Statement

The University of Massachusetts Amherst is committed to providing an equal educational opportunity for all students. If you have a documented physical, psychological, or learning disability on file with Disability Services (DS), you may be eligible for reasonable academic accommodations to help you succeed in this course. If you have a documented disability that requires an accommodation, please notify me within the first two weeks of the semester so that we may make appropriate arrangements.

Academic Honesty Statement

Since the integrity of the academic enterprise of any institution of higher education requires honesty in scholarship and research, academic honesty is required of all students at the University of Massachusetts Amherst. Academic dishonesty is prohibited in all programs of the University. Academic dishonesty includes but is not limited to: cheating, fabrication, plagiarism, and facilitating dishonesty. Appropriate sanctions may be imposed on any student who has committed an act of academic dishonesty. Instructors should take reasonable steps to address academic misconduct. Any person who has reason to believe that a student has committed academic dishonesty should bring such information to the attention of the appropriate course instructor as soon as possible. Instances of academic dishonesty not related to a specific course should be brought to the attention of the appropriate department Head or Chair. Since students are expected to be familiar with this policy and the commonly accepted standards of academic integrity, ignorance of such standards is not normally sufficient evidence of lack of intent (http://www.umass.edu/dean_students/codeofconduct/acadhonesty/).