Scribd
Upload
88 views5 pages

CS598 - Deep Learning For Healthcare Syllabus

Uploaded by

PRITAM PAUL
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
88 views5 pages

CS598 - Deep Learning For Healthcare Syllabus

Uploaded by

PRITAM PAUL
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/ 5

Sample syllabus - students will receive the detailed syllabus at the beginning of

the semester enrolled in th course.

CS 598 Deep Learning for Healthcare

Instructor:
Jimeng Sun

Course Description
Welcome to Deep Learning for Healthcare. This course covers deep learning (DL) methods,
healthcare data and applications using DL methods. The courses include activities such as video
lectures, self guided programming labs, homework assignments (both written and programming),
and a large project.

The first phase of the course will include video lectures on different DL and health applications
topics, self-guided labs and multiple homework assignments. In this phase, you will build up
your knowledge and experience in developing practical deep learning models on healthcare data.
The second phase of the course will be a large project that can lead to a technical report and
functioning demo of the deep learning models for addressing some specific healthcare problems.
We expect the best projects can potentially lead to scientific publications.

Course Objectives
You are expected to learn deep learning models such as deep neural networks, convolutional
neural networks, recurrent neural networks, autoencoder, attention models, graph neural
networks and deep generative learning. You will also get a chance to learn different healthcare
applications using DL methods such as clinical predictive models, computational phenotyping,
patient risk stratification, treatment recommendation, clinical natural language processing, and
medical imaging analysis. Besides learning DL algorithms, the course will focus on hands-on
experiences for data scientists and machine learning engineers to implement various practical
healthcare models on diverse medical data. You will learn popular deep learning frameworks like
pytorch, and data science software like jupyter notebook.

Prerequisites
Basic machine learning will be helpful but not strictly required. You should have good
programming skills in python and good understanding in linear algebra and calculus. You should
also have sufficient system knowledge such as using linux, setting up programming environments
on the cloud.
Textbook and Readings
A textbook is being developed by the instructor. The corresponding chapters will be provided to
the students. Also relevant research papers will be provided to you. You are also encouraged to
conduct your own literature review especially during the project phase.

Elements of This Course


The following elements are in this course:
● Video lectures: They are recorded by the instructor to cover technical topics about deep
learning and related healthcare applications.
● Labs: They are self-guided study materials that provide the step by step instructions of
the programming tasks related to building deep learning models and manipulating
healthcare data.
● Homework assignments: They contain both the written parts and the programming parts.
The written parts involve mathematical derivation and short answer questions. The
programming parts involve completing data processing scripts, building and evaluating
DL models.
● Project: a large group project at the second phase of the course.
○ Each project team consists of 1 to 4 students.
○ Project topics are provided in the project overview document in the course. With
permission from the instructor, a different project can be pursued as long as they
are about deep learning for healthcare problems. The project should be
exclusively done for this course. The students should NOT use this project from
or for other courses or for other purposes (such as part of your daily job).
○ Project proposal: a short clearly written description of your project that provides
the overview of your project. It should clearly describe the data, the task and the
evaluation metric and the key related works.
○ Project draft: a complete write-up about the project including some preliminary
experiment results.
○ Project presentation: a 5-min video presentation that summarizes the key results
from your project. It should describe the task, the data, the method and the
result. It should be within 5-min.
○ Project final report: a well written report that summarizes all the findings from
your project. It should look like a publishable technical report.

Grading Distribution and Scale

Component % of the total grade

Homework assignments 50% (10% each)


Weekly reflection 15%

Project proposal 3%

Project draft 7%

Project final presentation 10%

Project report 15%

Course Outline

Week # Dates Activities


1 Introduction
2 Machine learning basics
3 Health data
4 Deep Neural Networks (DNN)
5 Embedding
6 Convolutional Neural Networks (CNN)
7 Recurrent Neural Networks (RNN)
8 Autoencoders
9 Attention Models
10 Graph Neural Networks
11 Memory network
12 Deep generative models
13- 14 Project activities
15- 16 Project presentation
Assignment Deadlines
For all assignment deadlines, please refer to the Course Assignment Deadlines, Late Policy,
and Academic Calendar page.

Student Code and Policies


A student at the University of Illinois at the Urbana‑Champaign campus is a member of a
University community of which all members have at least the rights and responsibilities common
to all citizens, free from institutional censorship; affiliation with the University as a student does
not diminish the rights or responsibilities held by a student or any other community member as a
citizen of larger communities of the state, the nation, and the world. See the University of Illinois
Student Code for more information. Academic Integrity All students are expected to abide by the
campus regulations on academic integrity found in the Student Code of Conduct. These standards
will be enforced and infractions of these rules will not be tolerated in this course. Sharing, copying,
or providing any part of a homework solution or code is an infraction of the University’s rules on
academic integrity. We will be actively looking for violations of this policy in homework and project
submissions. Any violation will be punished as severely as possible with sanctions and
penalties typically ranging from a failing grade on this assignment up to a failing grade in
the course, including a letter of the offending infraction kept in the student's permanent
university record. Again, a good rule of thumb: Keep every typed word and piece of code your
own. If you think you are operating in a gray area, you probably are. If you would like clarification
on specifics, please contact the course staff.

Disability Accommodations
Students with learning, physical, or other disabilities requiring assistance should contact the
instructor as soon as possible. If you’re unsure if this applies to you or think it may, please
contact the instructor and Disability Resources and Educational Services (DRES) as soon as
possible. You can contact DRES at 1207 S. Oak Street, Champaign, via phone at (217) 333-
1970, or via email at [email protected].

Late Policy
Each student is allowed 2 days of late submission in total to be used for HOMEWORK
only. You can split the 2 days grace period across two different homework (20 hours
will be counted as 1 day and 30 hours counted as 2 days). Once you have used up your
late days, late assignments will be penalized at a rate of 10% per day (10% of the total
points not 10% of your score. If your score is 60 but you are late for 1 day, your score
will become 50). Assignments more than 5 days late will not be accepted. Also, you
can't apply the late days toward the final project or Kaggle competition. We rarely
cons ider other homework extens ion reques ts due to the volume of the clas s , s o pleas e
s chedule your arrangements well in advance.

You might also like