Scribd
Upload
23 views3 pages

Syllabus For CSC 578 - Neural Networks and Deep Learning, Spring 2021

Uploaded by

Jayashree. S
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
23 views3 pages

Syllabus For CSC 578 - Neural Networks and Deep Learning, Spring 2021

Uploaded by

Jayashree. S
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Syllabus for CSC 578: Neural Networks and Deep Learning, Spring

2021

Overview

This course focuses on the algorithms, implementation, and application of neural networks for
learning about data. Students will learn how neural networks represent data and learn in supervised
and unsupervised contexts with applications to language processing, classification, and regression
problems. Topics include learning algorithms, and optimization methods, deep learning methods for
deriving deep representations from surface features, recursive networks, Boltzmann machines and
convolutional networks.

Learning Outcomes

By the end of this course you should be able to:

Describe the mathematical foundations underlying neural networks


Use matrix programming techniques to implement and modify a learning algorithm
Implement deep learning techniques for dealing with structure in language and image
processing applications
Select an appropriate neural network / deep learning approach for a given task

Prerequisites

CSC 412 and (DSC 478 or CSC 480)

Important Note: This course assumes that you have mature programming abilities. You will
not be taught how to make algorithms or write code. You should know that coming in. If
you're unsure about your programming abilities, you should wait and take this class later.

Textbooks

NNDL: Neural Networks and Deep Learning, by Michael Nielsen. Available for free online.
DLB: Deep Learning Book, by Goodfellow, Bengio, and Courville. MIT Press. Also
available for free online, or bound from your favorite bookseller. (Note: We will use only a
relatively small portion of this book.)

Attendance

It's your responsibility to work the supplied materials, including videos and readings to make sure
that you get the grade you want in the class.

Class Plan

The following class plan is tentative and subject to change as the course progresses.
Class 1: (4/1) Course overview. Intro to NNs
Class 2: (4/8) How NNs work
Class 3: (4/15) Improving Neural Nets
Class 4: (4/22) Improving NNs II and Intro to Deep Learning
Class 5: (4/29) More Deep Learning: Convolutional NNs
Class 6: (5/6) Intro to Recurrent Networks
Class 7: (5/13) Recurrent Neural Networks 2: Practical Details
Class 8: (5/20) Attention with RNNs
Class 9: (5/27) Natural Language Processing
Class 10: (6/3) Misc Topics. Wrap-up

Instructor Information
Email [email protected]
Home Page http://reed.cs.depaul.edu/peterh/
Phone 312-362-5736
Office Hours Via Zoom: Monday and Thursday: 3:30-5:00pm, or by arrangement
Address CDM Center 717

Assessment

Your final grade will be based on:

Homeworks 70%
Final Project 30%

The grading scale will be:

Percent Grade
93.3 A
90 A-
86.6 B+
83.3 B
80 B-
76.6 C+
73.3 C
70 C-
66.6 D+
60 D
< 60 F
Late submission policy

Unless otherwise stated, written assignments are due via D2L at the time and date posted on the
course homepage. You are expected to complete all of the written assignments by the deadline. Late
homework submissions will be accepted via D2L with the following penalty:

If assignment is turned in… Penalty will be…


within 3 days of due date 10% of the total points for each day it is late
3 days or more after due date Will NOT be accepted

Fairness to the whole class is an important foundation for the course.

On Plagiarism

You are encouraged to discuss all homeworks and projects with your classmates. You are, however,
required to complete the assignments on your own. In particular, this means that you are not
allowed to "cut and paste" text from anywhere else, or to paraphrase someone else's work, or to
write your answers along with someone else. Plagiarism is a serious academic offense, and is dealt
with very seriously. It will result in at least a score of 0 on the assignment, and could result in
failure from the course, or dismissal from the university.

All assignments will be submitted to "Turn it in" for automatic plagiarism testing. This system is
very good at finding things that have been copied, so just don't do it.

School policies on instructor evaluation, email, plagiarism and incompletes.

You might also like