COMPSCI 682 Neural Networks: A Modern Introduction

This 3-credit course will focus on modern and practical methods for deep learning. We will begin with a overview of simple classifiers, such as perceptrons and logistic regression, and move on to standard neural networks, convolutional neural networks, and elements of recurrent neural networks and transformers. The emphasis will be on the fundamentals and practical application, rather than an in-depth theoretical approach. While the majority of the applications discussed will focus on computer vision, we will also cover some natural language processing (NLP) applications. The programming components will be based on Python and its associated packages, such as Numpy and PyTorch. Students should have a strong background in Linear Algebra, Probability and Statistics, and Multivariate Calculus, and an ability to program in Python.

An Important Message Regarding Course Expectations!

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 (


Prof. Subhransu Maji
Office Hour: Wed 3-4pm, CS274
Prof. Chuang Gan
Office Hour: Fri 9-10am, Zoom

Teaching Assistants

Oindrila Saha
TA Hours: Mon/Wed 1-2pm, Mon Zoom, Wed CS207

Max Hamilton
TA Hours: Mon/Wed 2-3pm, CS207

Junyan Li
TA Hours: Wed/Fri 10-11am, LGRT T222

Ashish Singh
TA Hours: Thur/Fri 4-5pm, CS207

Eddie Cunningham
TA Hours: Tue/Thur 9-10am, Tue Zoom, Thur CS207

Ke Xiao
TA Hours: Tue/Fri 11am-12pm, Zoom


Tue & Th 1:00PM - 2:15PM
Morrill Sci Ctr (1) Room N375

Optional Discussions

Fri 9:00-10:00 am
CS 142

Grading Policy

Assignment #1: 15%
Assignment #2: 15%
Assignment #3: 15%
Midterm: 15%
Final Project: 40%

Course Discussions

Discussions on Piazza.

Discussion Forum »


There will be 3 homework assignments through the semester.

View details »


Many thanks to Jiajun Wu, Fei-Fei Li and Andrej Karpathy for graciously letting us use materials from the Stanford CS231n.