University of Alberta

Microcredential in Physics-Informed Neural Networks

January 29-February 16, 2024

Instructor: Vakhtang Putkaradze

E-mail: [email protected]
Web Page: https://sites.ualberta.ca/~putkarad/

Office Hours: Virtual

Instructor — by appointment
Youssef Mousaaid: Wednesdays (Jan 31, Feb 7, and Feb 14): 1-3 pm
Serafim Grubas: Fridays (Feb 2, Feb 9, Feb 16): 1-3 pm
Links to YM and SG office hours will be posted in Announcements

Lecture Room & Time: Virtual, MWF 3-7 pm from Jan 29-Feb 16

COURSE CONTENT

Microcredential description
To give participants tools to understand and use the science behind Physics-Informed Neural
Networks (PINNs), the advantages of these methods, and the limitations in their use. Upon
successful completion of the course, the participants will receive a certi cate of completion. This
course cannot be taken for credit at the University of Alberta.

Target audience
Graduate students (PhD and MSc) in science and engineering, employees of local companies,
National laboratories and others interested in applications of PINNs.

Prerequisites:
Knowledge of ordinary and partial differential equations on an undergraduate level. Ability to
program in Python.
Note: The knowledge of either stochastic processes, probability, or neural networks is not
assumed. All the necessary background in these elds will be given during the course.

Course outline, with the number of lecture hours

The total planned lecture time is 24 hours. In addition, practical exercises and programming are
planned using the ratio of 1 in-class problem-solving practice hour per 2 hours of theory lectures,
and one hour of discussion.
fi
fi
Week Topic Theory In-class
hrs practice
Hrs

1 The basic theory of neural networks and approximation theory 3 1

1 Theory of automatic differentiation and Neural differential 2 1

equations. Use of open-source Python libraries to develop
PINNs
1 Mathematical models and differential equations: ODEs (linear/ 3 2
Airy/Bessel), PDEs: Wave, viscous/inviscid Burgers equation,
KdV, Eikonal, Camassa-Holm equations
2 Approximation of ODEs/PDEs by neural networks using 2 1
automatic differentiation; incorporating initial conditions
2 Solution of ODEs/PDEs with PINNs, practice using open- 2 1
source Python libraries
2 Analysis of solutions obtained by PINNs and comparison with 2 1
theoretical predictions
3 Analysis of solutions obtained by PINNs and comparison with 2 1
theoretical predictions
3 Parameter determination using PINNs from data 2 1

3 The noise in data and stochasticity effects 2 1

3 Large-scale computing with PINNs and industrially relevant 4 2

applications, as suggested by the audience

Total theory hours: 24; in-class practice: 12, total course time: 36 hours, with about 72 hours of
expected work by students.

Microcredential outcomes
By the end of the course, the participants will be able to construct PINNs for particular science or
engineering problems, generate the solutions, determine the parameters whenever necessary and
appropriate, and analyze the correctness of the solutions.

Microcredential delivery
The course will be delivered online. The participants will use Jupyter Notebooks in Google
Colab in order to avoid issues with the installation of libraries on participants’ computers. The
course is going to be delivered over three weeks of online instruction, three times per week of, 4
hours per day. Zoom link to the course will be posted on eClass; please do not share that link.

Microcredential Resources and Announcements: on eClass external.

Microcredential fee: None

LEARNING RESOURCES

Required Textbook and/or Other Major Course Materials: Jupyter notebooks

containing lecture notes and exercises will be provided through eClass.

Recommended or Optional Learning Resources: Additional resources (e.g.

references to research papers, monographs etc) will be added to eClass as necessary.

GRADE EVALUATION
Successful completion:
There are two options for completing the course.
• For regular microcredential pass (audit-level), one needs to show class participation,
which can take different forms: participating in the class, reading and running Jupyter
notebooks, performing homework etc.
• For microcredential pass on the developer level, the participants will have to give
provide PDFs for at least six homework problems from three chapters of the course. A
guide to the homework will be provided. Participants are welcome to follow this guide
or write the solutions themselves.

Statement of Expectations for AI Use: Any AI use is allowed, but discouraged. Please be
careful as programs provided by ChatGPT are often incorrect and require much more time to
make them functional than writing these programs from scratch.

REMOTE DELIVERY CONSIDERATIONS

Technology for Remote Learning:

To successfully participate in remote learning in this course, the participants will need to
have access to a computer with an internet connection that can support the tools and
technologies the University uses to deliver content, engage with instructors, TAs, and
fellow students, and facilitate assessment and examinations.
Recordings of Synchronous Activities: The lectures will not be recorded.

STUDENT RESPONSIBILITIES

Academic Integrity and Student Conduct:

The University of Alberta is committed to the highest standards of academic integrity

and honesty, as well as maintaining a learning environment that fosters the safety,
security, and the inherent dignity of each member of the community, ensuring students
conduct themselves accordingly. While this is not an official for-credit course at the
University of Alberta, the participants are expected to be follow the standards of
academic honesty and appropriate student conduct, and to uphold the policies of the
University in this respect. Participants are particularly urged to familiarize themselves
with the provisions of the Code of Student Behaviour and the Student Conduct Policy,
and avoid any behaviour that could potentially result in suspicions of academic
misconduct (e.g., cheating, plagiarism, misrepresentation of facts) and non-academic
misconduct (e.g., discrimination, harassment, physical assault). Academic and non-
academic misconduct are taken very seriously and can result in suspension or
expulsion from the University.

All students are expected to consult the Academic Integrity website for clarification on
the various academic offences. All forms of academic dishonesty are unacceptable at
the University. Any suspected academic offence in this course will be reported to the
College of Natural and Applied Sciences. Suspected cases of non-academic
misconduct will be reported to the Dean of Students. The College, the Faculty of
Science, and the Dean of Students are committed to student rights and responsibilities,
and adhere to due process and administrative fairness, as outlined in the Code of
Student Behaviour and the Student Conduct Policy. Anyone who is found in violation is
likely to receive a sanction. Typical sanctions for academic misconduct include conduct
probation, a failing grade in the course, a remark on the transcript, and a
recommendation for suspension or expulsion. Sanctions for non-academic misconduct
include conduct conditions, fines, suspension of essential or non-essential University
services and resources, and suspension or expulsion from the University.

Appropriate Collaboration: Participants are allowed to collaborate on solutions should

they desire to do so.
Students Eligible for Accessibility-Related Accommodations:
In accordance with the University of Alberta’s Discrimination, Harassment, and Duty to
Accommodate policy, accommodation support is available to eligible students who
encounter limitations or restrictions to their ability to perform the daily activities
necessary to pursue studies at a post-secondary level due to medical conditions and/or
non-medical protected grounds. Accommodations are coordinated through the
Academic Success Centre, and students can learn more about eligibility on the Register
for Accommodations website.

It is recommended that students apply as early as possible in order to ensure sufficient

time to complete accommodation registration and coordination. Students are advised to
review and adhere to published deadlines for accommodation approval and for specific
accommodation requests (e.g., exam registration submission deadlines). Students who
request accommodations less than a month in advance of the academic term for which
they require accommodations may experience unavoidable delays or consequences in
their academic programs, and may need to consider alternative academic schedules.

Recording and/or Distribution of Course Materials:

Audio or video recording, digital or otherwise, of lectures, labs, seminars or any other
teaching environment by students is allowed only with the prior written consent of the
instructor or as a part of an approved accommodation plan. Student or instructor
content, digital or otherwise, created and/or used within the context of the course is to
be used solely for personal study, and is not to be used or distributed for any other
purpose without prior written consent from the content author(s).

Learning and Working Environment:

The Faculty of Science is committed to ensuring that all students, faculty and staff are
able to work and study in an environment that is safe and free from discrimination,
harassment, and violence of any kind. It does not tolerate behaviour that undermines
that environment. This includes virtual environments and platforms.

If you are experiencing harassment, discrimination, fraud, theft or any other issue and
would like to get confidential advice, please contact any of these campus services:
● Office of Safe Disclosure & Human Rights: A safe, neutral and confidential space
to disclose concerns about how the University of Alberta policies, procedures or
ethical standards are being applied. They provide strategic advice and referral on
matters such as discrimination, harassment, duty to accommodate and wrong-
doings. Disclosures can be made in person or online using the Online Reporting
Tool.
● University of Alberta Protective Services: Peace officers dedicated to ensuring
the safety and security of U of A campuses and community. Staff or students can
 contact UAPS to make a report if they feel unsafe, threatened, or targeted on
campus or by another member of the university community.
● Office of the Student Ombuds: A confidential and free service that strives to
ensure that university processes related to students operate as fairly as possible.
They offer information, advice, and support to students, faculty, and staff as they
deal with academic, discipline, interpersonal, and financial issues related to
student programs.
● Office of the Dean of Students: They can assist students in navigating services to
ensure they receive appropriate and timely resources. For students who are
unsure of the support they may need, are concerned about how to access
services on campus, or feel like they may need interim support while you wait to
access a service, the Dean of Students office is here to help.

Feeling Stressed, Anxious, or Upset?

It's normal for us to have different mental health experiences throughout the year. Know
that there are people who want to help. You can reach out to your friends and access a
variety of supports available on and off campus at the Need Help Now webpage or by
calling the 24-hour Distress Line: 780-482-4357 (HELP).

Student Self-Care Guide:

This Self-Care Guide, originally designed by the Faculty of Native Studies, has broader
application for use during students’ learning. It provides some ideas and strategies to
consider that can help navigate emotionally challenging or triggering material.

Policy about course outlines can be found in Course Requirements, Evaluations

Procedures and Grading of the University Calendar.

Land Acknowledgement:
The University of Alberta respectfully acknowledges that we are situated on Treaty 6
territory, traditional lands of First Nations and Métis people.

To learn more about the significance of this land acknowledgement, please read this
useful article and associated links to more information.

Disclaimer:
Any typographical errors in this Course Outline are subject to change and will be
announced in class.

Copyright:
Dr. Vakhtang Putkaradze, Department of Mathematical and Statistical Sciences, Faculty
of Science, University of Alberta, 2024.