User Tools

Site Tools


cs474_f2020

Welcome to CS474, Fall 2020!

Welcome to the most exciting class on campus! We will study the basics of deep neural networks (DNNs), including high-level philosophy, basic mathematics and models, training, initialization, and regularization; common usages such as classification, regression, reinforcement learning and generative models; interesting applications like style/content transfer, language translation, audio processing, language and image synthesis/generation, and control; as well as miscellaneous topics including robustness, visualization, interpretability/understandability, and ethical considerations.

Quick links

Text and Reading

There is no required text for the class; instead, required readings will be found online and in freely available research papers. In addition, optional, supplemental readings are suggested from the book, Deep Learning (https://deeplearningbook.org/), by Goodfellow, Bengio and Courville.

Both types of reading are given on the course schedule. You are responsible for reading the material for a given day prior to that day's lecture. In addition, each week you will take a simple quiz on learning suite indicating how much of the assigned reading you completed.

Attendance and Participation

This is a synchronous, remote-delivery class. However, class attendance and participation are expected. Lectures will not be recorded, and will not be made available afterwards. This is not because I feel the need to have students in class; instead, it is because your attendance and participation guarantee you a better learning experience.

I expect cameras to be on when you join our zoom class. This indicates that you are fully engaged; we will be doing various break-outs, and I expect everyone to participate.

Make sure you have done the reading and tried to understand on your own before you ask questions. When you don't understand something, ask!

Programming Projects

There will be 10 programming projects throughout the semester. For each project, you will become familiar with useful techniques by implementing (part of) a DNN model. You will interact with a Jupyter notebook, including writing code and answering questions or providing requested output from running your code.

In addition, there will be a final project that you will design and build yourself, and which will serve as your final exam. Additional information for this project is contained in the link below.

More information on projects can be found on the projects page.

Late policy

All readings and projects are due by 11:30pm on the date indicated. It is your responsibility to ensure that you've done everything required and that the required results are included and clear.

Late work is not accepted. The reason for this is because we release fully-formed “answer notebooks” to improve your learning.

All assignments must be submitted through Learning Suite. Note that waiting until the last minute to submit through Learning Suite can be unreliable, so plan to submit early. It is in your best interest to submit whatever you can before the deadline. Probably the best way to make sure you are not unpleasantly surprised is to submit incrementally: submit what you have early, and then continue to improve your work and resubmit as you make improvements, up until the deadline.

Note that the schedule is designed to give you time between when we discuss in class the concepts needed for a project and when it is due. Please start early and make use of that time to do a good job. If you do not get the entire project completed by the deadline, make sure you submit what you have.

In my experience, one key to success, in this class, in our profession and in life in general, is being organized and meeting deadlines. The no-late-work-policy is in large part to help you be successful and be able to continue progressing and focusing on new material. Please submit your work on time!

Of course, if you have extenuating circumstances that warrant an exception to the no late work policy, please talk to me as soon as possible.

Grading

Grading will be done with the standard scale. An approximate breakdown is as follows:

  • Category Weight
  • Reading 10.5%
  • Minor projects 8.1%
  • Major projects 56.7%
  • Final project 24.7%

Although your final class grade will not be available until the end of the term, a cumulative point total will be available online and will be updated regularly. You should check this periodically to ensure that my records are in accordance with the work you have done. Please bring any discrepancies to my attention immediately, as these things are usually easily resolved early and are often much more difficult as time passes.

Working Together

You may work together with other members of the class; in fact, you are strongly encouraged to do so; however, do NOT turn in other people's work (of course, this includes material you might find on the internet). This is a fine line that may require some judgment on your part. Examples of acceptable collaboration: discussing projects and solutions with others in the class; posting questions and/or answers to questions on the class slack channel; comparing learning results and conclusions from programming assignments with other class members, using online API documentation to learn syntax, searching stackoverflow for examples of how to use a language feature. Unacceptable collaboration would be simply copying code from a friend (or the internet) or allowing someone else to copy code.

Preventing and Responding to Sexual Misconduct

In accordance with Title IX of the Education Amendments of 1972, Brigham Young University prohibits unlawful sex discrimination against any participant in its education programs or activities. The university also prohibits sexual harassment—including sexual violence—committed by or against students, university employees, and visitors to campus. As outlined in university policy, sexual harassment, dating violence, domestic violence, sexual assault, and stalking are considered forms of “Sexual Misconduct” prohibited by the university.

University policy requires all university employees in a teaching, managerial, or supervisory role to report all incidents of Sexual Misconduct that come to their attention in any way, including but not limited to face-to-face conversations, a written class assignment or paper, class discussion, email, text, or social media post. Incidents of Sexual Misconduct should be reported to the Title IX Coordinator at t9coordinator@byu.edu or (801) 422-8692. Reports may also be submitted through EthicsPoint at https://titleix.byu.edu/report or 1-888-238-1062 (24-hours a day).

BYU offers confidential resources for those affected by Sexual Misconduct, including the university’s Victim Advocate, as well as a number of non-confidential resources and services that may be helpful. Additional information about Title IX, the university’s Sexual Misconduct Policy, reporting requirements, and resources can be found at http://titleix.byu.edu or by contacting the university’s Title IX Coordinator.

Students With Disabilities

BYU is committed to providing reasonable accommodation to qualified persons with disabilities. If you have any disability that may adversely affect your success in this course, please contact the University Accessibility Center at 422-2767. Services deemed appropriate will be coordinated with the student and instructor by that office.

Creating a Diverse and Inclusive Environment

Our classroom participation and behavior are guided by our mission statement, the BYU honor code, and principles of Christian discipleship. It is imperative that we value and respect every person as a child of Heavenly Parents who has divine worth. Consequently, we need to take steps to listen to, learn from, and love one another by striving to consider thoughtfully the opinions of others and use language that is polite, considerate, and courteous even when we strongly disagree. It is essential to create an educational environment that ensures “the gift of personal dignity for every child of God”. This includes embracing one another compassionately and “eliminat[ing] any prejudice, including racism, sexism, and nationalism…regardless of age, personal circumstances, gender, sexual orientation, or other unique challenges.” It is vital to delight in individuality and welcome diverse perspectives and experiences as we “work tirelessly to build bridges of understanding rather than creating walls of segregation.” To accomplish these goals we seek unity in higher principles of equity, charity, collaboration, and inclusiveness in order to build an environment in which all students, faculty, and staff can participate in, contribute to, and benefit equally from the academic community.

cs474_f2020.txt · Last modified: 2020/08/31 11:44 by wingated