CSE510 - Edge Intelligence and Computing
TuTh 7:05 - 8:20 PM
ZOOM - ONLINE
https://buffalo.zoom.us/j/98716185764?pwd=dmFQRm05QUZZQXZOaE1MM01Ed2NxUT09
Course Syllabus
This semester will continue to be a challenge, and your instructors are committed to making this course as engaging as possible. We hope that you will take this seriously and work with us to make this as enjoyable as possible.
Course attendance is on the live link is mandatory, although I will record classes in case there are problems with connections. You are expected to participate in class through online polls and questions. These polls and questions will be noted and used at the instructors' discretion when considering the final grade. There may also be "pop quizzes" that will be used in the same way, not as a formal part of your grade, but rather to make sure you are engaged. They will be more a barometer for you than a formal assessment on our part.
Thank you for you signing up for this class, and please let us know what can be done to improve the course, not only at the end but at any time, and we will do our best to address any issues that may come up.
|
Instructor: |
Dr. David Doermann |
|
Office: |
113M Davis Hall |
|
E- mail: |
Prefers to be contacted through Piazza |
|
Office Hours: |
Tuesdays 12- 2, or by appointment |
|
Zoom Link |
See Piazza - Resources - Staff |
|
Instructor: |
Dr. Baochang Zhang |
|
Office: |
|
|
E- mail: |
Prefers to be contacted through Piazza |
|
Office Hours: |
TBD |
|
Zoom Link |
See Piazza - Resources - Staff |
Lectures, Homeworks, Quizzes, Projects, and a final exam during the 14- week semester.
This course is an introduction to those areas of Artificial Intelligence that deal with fundamental issues and techniques of edge computing. The emphasis is on both conventional methods and deep learning for efficient computing. Topics to be covered include convolutional kernels and Gabor filters, advanced and efficient features for localization, efficient feature reduction, efficient learning and classifiers, neural network and deep learning, compressed neural networks, quantized neural networks, deep learning and efficient object detectors, neural architecture search, object tracking, and object recognition.
The material is based on graduate- level texts augmented with research papers, as appropriate.
- To understand the main factors to build edge computing systems are and how artificial intelligence technologies affect efficient computing.
- To be able to use convolutional filters and Gabor filters for efficient object representation. (Project)
- To know to extract pixel- level features for localization.
- To know to calculate efficient feature reduction based on subspace learning.
- To know how to build efficient learning and classifiers. (Project)
- Understand how to build neural networks and deep learning networks, and know their difference(s).
- To know how to compress neural networks based on pruning.
- To know how to quantize neural networks. (Project)
- To be able to build efficient object detectors based on deep learning.
- To Understand neural architecture search methods.
- To know how to build object tracking and object recognition systems.
- Computer Vision and Machine Perception by Baochang Zhang (Gruyter 2020)
- Papers available online as cited in the schedule
- Class attendance and participation is expected
- You are responsible for ALL materials presented in class and assigned to read
- Quizzes will be given during class time only.
- There will be three projects
- Regular deliverables on the project will be graded during the course
- All assignments will be graded out of 100 points and weighted according to the table below
- All assignments will be turned in via UB Learns
- Quizzes and tests will be given online through the UB Learns system. For some quizzes and test, you will be required to install the Respondus browser
|
Weighting |
Assessment / Assignment |
Number |
|
30% |
Quizzes |
4 |
|
50% |
Projects |
3 |
|
20% |
Final |
1 |
|
100% |
|
|
- It is entirely your responsibility to follow the policies outlined here and by the university
- Please ask the instructor(s) if you have questions.
Late Submission Policy
- Completed homework and project deliverables are to be submitted by their deadline (11:59 PM).
- For homework, you will have up to 3 days to receive a grade reduced by 50%. No additional late days are allowed.
- Projects: You will be allowed a total of 3 days/partial day late submissions throughout the semester. Each late day beyond the three allowed will reduce your grade by 50%.
- No individual project/homework will be accepted after three days late.
Regrading Policy to Correct Grading Errors
- Assignments, quizzes, and exams may be submitted for regrading to correct grading errors.
- Regrade requests are due no later than one (1) week after the scores are posted.
- Regrade requests must be clearly written and attached to the assignment.
- When work is submitted for regrade, the entire work may be regraded, which may result in a lower grade.
- Work done in pencil may not be considered for regrading.
Exam Policy
- No makeup exams will be given except in provably extreme circumstances.
- Notify your instructor 24 hours prior to the exam via e- mail if you are going to miss it. If it is medically impossible for you to give prior notice, please obtain a note from a physician detailing the period (and the reason) you were medically incapable of communicating with the instructor.
- If you miss an exam/quiz because of sickness or similar reasons, visit a physician and obtain a note detailing the period and why you were medically incapable of taking the exam/quiz.
- You are responsible for knowing about the exam date. Please plan your travel and other activities accordingly.
Grading Policy
- No "I" (Incomplete) will be given except under provably extreme circumstances.
- There is no grade negotiation at the end of the semester.
Disabilities
- If you have a diagnosed disability (physical, learning, or psychological) that will make it difficult for you to carry out the course work as outlined or that requires accommodations such as recruiting note- takers, readers, or extended time on exams or assignments, please advise the instructor during the first two weeks of the course so that we may review possible arrangements for reasonable accommodations. Also, if you have not yet done so, contact the Office of Disability Services.
All work must be your own
- Do not take the answers, words, ideas, or research findings of other people as yours; cite and acknowledge properly, and develop your ideas.
- No cheating
- According to departmental policy, any violation of academic integrity will result in a Failing Grade for the course and termination of departmental financial scholarship.
- Tools will be used to check similarity. Similar submissions will result in a Failing Grade for all involved parties.
- Use of a code from an online repository (when permitted) must include proper and clearly visible attribution in your report.