IS 757 - Deep Learning (Spring 2023)
Information Systems Department
University of Maryland Baltimore County
Baltimore, Maryland 21250
Departmental Office: Room ITE 404, ph. 410-455-3206
This course is an introduction to deep learning, a subset of machine learning, concerned with the development and application of modern neural networks. In this course, students will learn about the theory and application of deep learning. We will cover a range of topics from basic Neural Networks, Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN), Generative Adversarial Networks (GAN), and deep unsupervised learning. Besides, the students will learn how to apply the deep learning methods to solve real-world problems in several areas including computer vision, remote sensing, medical, language, and AI for social good applications and develop the insight necessary to use the tools and techniques to solve any new real-world problem.
Student learning outcomes: By the end of this course, you will be able to:
- discuss the history of deep learning and its current trends,
- explain the fundamentals and typical applications of deep learning,
- for a variety of modern deep learning architectures, algorithms, and modeling elements, be able to: explain, compare and contrast, and discuss their advantages, limitations, and applicability, and
- apply deep learning techniques to solve real problems.
Lecture time and venue: Thursdays 4:30PM - 7:00PM, Sherman Hall 014
Instructor: Dr. James Foulds
Instructor email: jfoulds [at] umbc [dot] edu. Please use Piazza for course-related questions, instead of email, so that everyone can benefit from the answers.
Instructor office hours: Thursdays 3:00 - 4:00 pm, ITE 447 (other times by appointment)
Piazza: Sign up for this course at https://piazza.com/umbc/spring2023/is757
Poll Everywhere: Vote on in-class poll questions at PollEv.com/jamesfoulds656 . Register your account for the course at https://PollEv.com/jamesfoulds656/register?group_key=mlU43oJi80alnLMur5ZRNySnr , by week 2 in order to get participation credits.
- You should be comfortable independently writing and debugging programs in Python.
- Although I will endeavor to keep the course as non-technical as possible, you will still need basic knowledge of linear algebra and calculus.
- It is strongly recommended that you take another course related to machine learning or data science before this one, e.g. IS603 or IS733. (Failing that, taking such a course concurrently would be better than nothing.)
Required TextbookJon Krohn, Grant Beyleveld, and Aglaé Bassens, Deep Learning Illustrated: A Visual, Interactive Guide to Artificial Intelligence (1st Edition), Addison-Wesley Data & Analytics, ISBN-13: 978-0135116692 , ISBN-10: 0135116694. is the course textbook. You will need this book for mandatory weekly readings.
Course Requirements and Grading
- Homeworks (4 of them) 18%. 6% each for your best 3 homeworks; the lowest score will be dropped)
- Group projects 32%:
- Proposal 5% (due 3/2/2023)
- Mid-term report 5% (due 4/13/2023)
- Poster 7% (presented in class 5/11/2023, digital copy due)
- Final report 15% (due Tuesday 5/16/2023, 11:59pm, by email)
- Midterm Exam 15% (take-home, 3/16/2023)
- Final Exam 25% (take home, 5/18/2023)
- Participation 10%
- Poll questions 8%
- At least two Piazza posts 2% (can be either questions or answers)
Projects will typically involve applying deep learning methods to solve a real-world problem. The group project will be done in groups of 3-5 students. Project deliverables are to be sent to me by email.Deliverable 1) Project proposal: list team members, define project topic, dataset, features as well as the deep learning architectures/methodologies that will be used in the project. (5%)
Deliverable 2) Project mid-term report: summarize progress made, methods tried, and results obtained (if any). Include a discussion of any challenges faced, and plans to resolve them. Feel free to ask me for advice. (5%)
Deliverable 3) Project poster presentation: A poster to be presented in a poster session in class. (7%)
Deliverable 4) Project final report: a full report on the project. The report should begin with a title and author names, and include at least the following sections: abstract (500 words maximum), introduction, background and related work, methodology, experimental results, references. (15%)
In this course, participation means more than just showing up. It also refers to contributing to everyone's learning, through active engagement in peer instruction exercises, in-class discussions, and Piazza questions/answers. Participation grades will be assessed as a percentage of peer instruction questions answered (correctly or not), with a 90% response rate being sufficient for full points, and by Piazza contributions. Two or more contributions (either questions or answers) on Piazza will earn you 1% of the final grade.
With respect to final letter grades, UMBC's Catalog states that an A indicates "superior" achievement; B, "good" performance; C, "not satisfactory"; D, "unacceptable"; F, "failure." There is specifically no mention of any numerical scores associated with these letter grades. Below is how grades may be assigned based on your final points, accumulated over the semester. Grades will be assigned using a plus/minus system. It is university policy that A+, D+, and D- are not assigned. I do not grade on a curve, so that everyone in the class has the opportunity to succeed.
|Final Grade||Letter Grade||Points when calculating GPA|
|91 - 100||A||4.0|
|89 - 90.99||A-||3.7|
|87 - 88.99||B+||3.3|
|81 – 86.99||B||3.0|
|79 - 80.99||B-||2.7|
|77 – 78.99||C+||2.3|
|71 – 76.99||C||2.0|
|69 - 70.99||C-||1.7|
|60 – 68.99||D||1.0|
|0 – 59.99||F||0.0|
Homework and Exam Policies
- Homeworks are due at the beginning of class on the dates specified, to be submitted via Blackboard. Late homeworks will not be accepted unless an extension is approved by me in advance. Requests for extensions must be made at least three days before the due date.
- In the event of class cancellation due to inclement weather, any hard-copy paper assignment or test will be due in the next class meeting. Electronic submissions will still be due on the original due date.
- Take-home exams will be administered as Blackboard assignments which will be made available by the morning of the exam day, and must be submitted by 11:59pm of the exam day.
ScheduleChapter numbers in the readings refer to the Krohn et al. textbook.
|2/2/2023||Week 1||Course introduction||Intro to deep learning||HW1 out||Ch 1|
|2/9/2023||Week 2||DL applications 1||NLP, word embeddings, AI art||Ch 2, Ch 3|
|2/16/2023||Week 3||DL applications 2||Game playing and AI, machine learning fundamentals, deep learning projects||HW1 due, HW2 out||Ch 4, Ch 14|
|2/23/2023||Week 4||DL fundamentals 1||Perceptrons, activation functions, Keras||Project groups formed by this date||Ch 5, Ch 6|
|3/2/2023||Week 5||DL fundamentals 2||Deep feedforward neural networks, training DNNs||Project proposal due||Ch 7, Ch 8|
|3/9/2023||Week 6||DL fundamentals 3||Advanced training of DNNs: batch normalization, regularization, data augmentation, momentum, Adam||HW2 due||Ch 9|
|3/16/2023||Week 7||Midterm Exam (Take-Home)||Content so far - DL fundamentals and applications||No class (since it's a take-home exam)|
|3/23/2023||Week 8||Spring Break||No class|
|3/30/2023||Week 9||DL for Computer Vision||CNNs||Ch 10|
|4/6/2023||Week 10||DL for NLP 1||RNNs, LSTMs, attention||HW3 out||Ch 11|
|4/13/2023||Week 11||DL for NLP 2||Transformer language models, pre-training, BERT, GPT||Project mid-term progress report due||The Illustrated Transformer, by Jay Alammar|
|4/20/2023||Week 12||Generative Adversarial Networks (GANs)||GAN architecture, GAN training, VAEs||HW3 due, HW4 out||Ch 12|
|4/27/2023||Week 13||DL for Healthcare||Guest lecture taught by Dr. Sanjay Purushotham||Reading TBD|
|5/4/2023||Week 14||Fairness and ethics for DL||Fairness definitions, fair word embeddings, final exam review||HW4 due||Reading TBD|
|5/11/2023||Week 15||Final Project Poster Presentation||Digital copies of posters due (before class, can update on Box until 11:59pm).|
|5/18/2023||Exam week||Final Exam (Take-Home)|| Take-home final exam (due 11:59pm Thursday 5/18/2023). |
Project final report due Tuesday 5/16/2023 (11:59pm)
The schedule may be subject to change. The summary and details columns are only a guideline of the content likely to be covered, and the dates on which material is covered may shift.
Traditional lectures will be augmented with active learning methods, primarily in the form of peer instruction exercises. Research has strongly indicated that active learning improves student outcomes in STEM fields versus traditional lecturing (Freeman et al., 2013). We will be using the Poll Everywhere service for polls and quizzes. You will need to bring a mobile device, laptop, or tablet to class in order to participate in the exercises. If you do not have a suitable device, please let me know as soon as possible.-->
Pre-class reading assignments will be given for each lesson, which are very important for learning, and for making the best use of our limited time together (a partially "flipped classroom" approach). These readings are therefore required.
COVID-19 PoliciesPlease see this Google doc for UMBC Policies and Resources during COVID-19.
UMBC's policies on academic integrity will be strictly enforced (see the University System of Maryland's policy document, UMBC's academic integrity overview page, the student academic conduct policy and the UMBC catalog). In particular, all of your work must be your own. Acknowledge and cite source material in your papers or assignments. While you may verbally discuss assignments with your peers, you may not copy or look at anyone else's written assignment work or code, or share your own solutions. Any exceptions will result in a zero on the assessment in question, and may lead to further disciplinary action. Some relevant excerpts from UMBC's policies, as linked to above, are:
- "By enrolling in this course, each student assumes the responsibilities of an active participant in UMBC's scholarly community in which everyone's academic work and behavior are held to the highest standards of honesty. Cheating, fabrication, plagiarism, and helping others to commit these acts are all forms of academic dishonesty, and they are wrong." (UMBC's academic integrity overview)
- "Students shall not submit as their own work any work which has been prepared by others." (USM policy document)
- "Students shall refrain from acts of cheating and plagiarism or other acts of academic dishonesty." (USM policy document)
- "Plagiarism means knowingly, or by carelessness or negligence, representing as one's own, in any academic exercise, the intellectual or creative work of someone else." (student academic conduct policy)
- "Cheating means using or attempting to use unauthorized material, information, study aids, or another person’s work in any academic exercise" (student academic conduct policy)
- The use of software tools to obfuscate your work in order to hide plagiarism is wrong, and is strictly prohibited.
- The use of language models such as ChatGPT for homeworks/exams/projects/etc. will be strictly regulated. Your work must be your own. While language models can be lightly used as a writing aid, their use must be limited to a small part of any subquestion and they must not contribute to the substance of your answer. Any use of these tools as a writing aid must be declared in your submission, with an explanation of why the work is your own and the use does not constitute plagiarism. If you have any questions, please check with me.
Accessibility and Disability Accommodations, Guidance and Resources
Accommodations for students with disabilities are provided for all students with a qualified disability under the Americans with Disabilities Act (ADA & ADAAA) and Section 504 of the Rehabilitation Act who request and are eligible for accommodations. The Office of Student Disability Services (SDS) is the UMBC department designated to coordinate accommodations that would create equal access for students when barriers to participation exist in University courses, programs, or activities.
If you have a documented disability and need to request academic accommodations in your courses, please refer to the SDS website at sds.umbc.edu for registration information and office procedures.
SDS email: disAbility@umbc.edu
SDS phone: (410) 455-2459
If you will be using SDS approved accommodations in this class, please contact me (instructor) to discuss implementation of the accommodations. During remote instruction requirements due to COVID, communication and flexibility will be essential for success.
Diminished mental health can interfere with optimal academic performance. The source of symptoms might be related to your course work; if so, please speak with me. However, problems with other parts of your life can also contribute to decreased academic performance. UMBC provides cost-free and confidential mental health services through the Counseling Center to help you manage personal challenges that threaten your personal or academic well-being.
Remember, getting help is a smart and courageous thing to do -- for yourself and for those who care about you. For more resources get the Just in Case mental health resources Mobile and Web App. This app can be accessed by clicking: counseling.umbc.edu/justincase.
The UMBC Counseling Center is in the Student Development & Success Center (between Chesapeake and Susquehanna Halls). Phone: 410-455-2472. Hours: Monday-Friday 8:30am-5:00pm.
Diversity Statement on RespectStudents in this class are encouraged to speak up and participate during our meetings. Because the class will represent a diversity of individual beliefs, backgrounds, and experiences, every member of this class must show respect for every other member of this class. (Statement from California State University, Chico’s Office of Diversity and Inclusion).
Family Educational Rights and Privacy Act (FERPA) Notice
Please note that as per federal law I am unable to discuss grades over email. If you wish to discuss grades, please come to my office hours.
Sexual Assault, Sexual Harassment, and Gender Based Violence and Discrimination
UMBC Policy and Federal Title IX law prohibit discrimination and harassment on the basis of sex in University programs and activities. Any student who is impacted by sexual harassment, sexual assault, domestic violence, dating violence, stalking, sexual exploitation, gender discrimination, pregnancy discrimination, gender-based harassment or retaliation should contact the University’s Title IX Coordinator to make a report and/or access support and resources:
Mikhel A. Kushner, Title IX Coordinator (she/her/hers)
410-455-1250 (direct line), email@example.com
You can access support and resources even if you do not want to take any further action. You will not be forced to file a formal complaint or police report. Please be aware that the University may take action on its own if essential to protect the safety of the community.
If you are interested in or thinking about making a report, please see the Online Reporting Form. Please note that, while University options to respond may be limited, there is an anonymous reporting option via the online form and every effort will be made to address concerns reported anonymously.
Notice that Faculty are Responsible Employees with Mandatory Reporting Obligations:
All faculty members are considered Responsible Employees, per UMBC’s Policy on Sexual Misconduct, Sexual Harassment, and Gender Discrimination. Faculty are therefore required to report any/ all available information regarding conduct falling under the Policy and violations of the Policy to the Title IX Coordinator, even if a student discloses an experience that occurred before attending UMBC and/or an incident that only involves people not affiliated with UMBC. Reports are required regardless of the amount of detail provided and even in instances where support has already been offered or received.
While faculty members want encourage you to share information related to your life experiences through discussion and written work, students should understand that faculty are required to report past and present sexual assault, domestic and interpersonal violence, stalking, and gender discrimination that is shared with them to the Title IX Coordinator so that the University can inform students of their rights, resources and support. While you are encouraged to do so, you are not obligated to respond to outreach conducted as a result of a report to the Title IX Coordinator.
If you need to speak with someone in confidence, who does not have an obligation to report to the Title IX Coordinator, UMBC has a number of Confidential Resources available to support you:
- The Counseling Center: 410-455-2472 / After-Hours 410-455-3230
- Center for Counseling and Consultation (Shady Grove Campus): 301-738-6273 (Messages checked hourly)
Online Appointment Request Form
- University Health Services: 410-455-2542
- Pastoral Counseling via Interfaith Center: 410-455-3657; firstname.lastname@example.org
- Women’s Center (for students of all genders): 410-455-2714; email@example.com.
- Shady Grove Student Resources, Maryland Resources, National Resources.
Child Abuse and Neglect:
Please note that Maryland law and UMBC policy require that I report all disclosures or suspicions of child abuse or neglect to the Department of Social Services and/or the police.
Hate, Bias, Discrimination and Harassment
UMBC values safety, cultural and ethnic diversity, social responsibility, lifelong learning, equity, and civic engagement.
Consistent with these principles, UMBC Policy prohibits discrimination and harassment in its educational programs and activities or with respect to employment terms and conditions based on race, creed, color, religion, sex, gender, pregnancy, ancestry, age, gender identity or expression, national origin, veterans status, marital status, sexual orientation, physical or mental disability, or genetic information.
Students (and faculty and staff) who experience discrimination, harassment, hate or bias or who have such matters reported to them should use the online reporting/referral form to report discrimination, hate or bias incidents. You may report incidents that happen to you anonymously. Please note that, if you report anonymously, the University’s ability to respond will be limited.
This course follows all other policy guidelines from the UMBC Office of Equity and Inclusion (OEI) listed at https://oei.umbc.edu/sample-title-ix-responsible-employee-syllabus-language/
- Equity and inclusion resources: https://oei.umbc.edu/oei-resources/
- i3b - Initiatives for Identity, Inclusion & Belonging: i3b.umbc.edu/
- Career Center's resources for diverse populations (including student organizations): http://careers.umbc.edu/students/resources/diverse/
- Office of International Education Services (IES): ies.umbc.edu/
- Information regarding the executive actions that were done in 2020: ies.umbc.edu/executive-actions/
- Wellness Initiative: wellness.umbc.edu/
- Counseling Center: counseling.umbc.edu/
- Women's Center: womenscenter.umbc.edu/
- Center for Women in Technology (CWIT): cwit.umbc.edu/
- Women Involved in Learning and Leadership (WILL) Program: gwst.umbc.edu/will/
- Sexual assault and relationship violence on-campus resources: womenscenter.umbc.edu/sexual-assault-and-relationship-violence-response-team-and-umbcs-voices-against-violence/
- Sexual misconduct policies and procedures (including filing a complaint): humanrelations.umbc.edu/sexual-misconduct/policies-and-procedures/
- Office of Student Disability Services: sds.umbc.edu/
- Academic Center for Student Athletes: https://umbcretrievers.com/sports/academiccenter
- Veteran Services veterans.umbc.edu/
- Graduate Student Association: gsa.umbc.edu/
- Graduate Student Association Writing Advisor: gsa.umbc.edu/writing-advisor/