User Tools

Site Tools


syllabus

Differences

This shows you the differences between two versions of the page.


Previous revision
syllabus [2022/09/06 09:35] – [Instructors] anderson
Line 1: Line 1:
-====== Overview ====== 
- 
-If you are having trouble registering for the on-campus section, you are welcome to [[https://www.online.colostate.edu/courses/CS/CS545.dot|register for the online section]]. 
- 
-This Overview is out-of-date.  It will be updated soon. 
- 
- 
- 
-===== Description ===== 
- 
-This course reviews fundamental methods and covers advanced concepts and methods involving deep neural networks for solving problems in data classification, prediction, visualization, and reinforcement learning.  
- 
-Students will //review// how to 
- 
-  * read data files of various formats and visualize characteristics of the data, 
-  * perform statistical analyses on multivariate data, 
-  * develop and apply classification algorithms to classify multivariate data, 
-  * develop and apply regression algorithms for finding relationships between data variables, 
-  * use the latest features in python, including jupyter notebooks, and 
-  * how to repeat experiments described in on-line tutorials, documentation, and publications in deep learning. 
- 
-Students will //learn// how to 
- 
-  * formulate and derive new algorithms for deep neural networks, 
-  * develop and apply reinforcement learning algorithms for learning to control complex systems, 
-  * interpret what a deep neural network has learned, 
-  * investigate the true advantages and limitations of recently developed, popular, complex deep network methods compared to simpler, older approaches, 
-  * write scientific reports on computational machine learning methods, results and conclusions, and 
-  * how to design, conduct, and report on novel machine learning experiments. 
- 
-For implementations we will be using 
-[[https://www.python.org/|Python]]. Previous experience with Python 
-and its numpy package is helpful.  To prepare for this course, please 
-download and install Python on your computer, and work through on-line 
-tutorials to help prepare for this course.  The 
-[[https://www.anaconda.com/distribution/|Anaconda distribution]] is 
-recommended, which is a free download for all platforms. 
- 
-CS440 is the prerequesite for this course.  However, CS445 provides a 
-more relevant background for the material in CS545.  Some of the CS445 topics 
-will be revisited in CS545.  The main difference between CS545 and 
-CS445 is the scale of the assignments, more material relates to 
-Pytorch and Tensorflow, and discussions of recent papers in the 
-research literature on deep learning. 
- 
-Class meetings will be a combination of lectures by the instructor, 
-discussions of students' questions, and some student presentations in 
-class. All questions are welcome, no matter how simple you think they 
-are; it is always true that someone else has a similar question. It is 
-critical that everyone in class respect each other when questions are 
-asked and answers are suggested and at all times. Please contact the 
-instructor when you have felt disrespect from other students, the 
-instructor, or the graduate teaching assistants. This may be anonymous 
-if you prefer. 
- 
-A lot of material will be covered in this course. Students are 
-expected to speak up in class with questions and observations they 
-have about the material. Do not expect to be able to complete all 
-assignments working on your own and without asking any questions. If 
-you find yourself wondering what the next step is in finishing an 
-assignment, please feel free to e-mail the instructor. You may also 
-discuss assignments with other students directly, or via our Piazza 
-Discussion board, but your code and report must be written by you.  Do 
-not post code on the Piazza Discussion board as part of your question 
-nor as part of your answer. 
- 
-You are expected to be familiar with the 
-[[http://www.cs.colostate.edu/advising/student-info.html|CS Department 
-policy]] on cheating and with the CS Department Code of Conduct found 
-at the department's 
-[[http://compsci.colostate.edu/policies-resources/|Policies & 
-Resources]] web page.  This course will adhere to the CSU Academic 
-Integrity Policy as found on the Student Responsibilities page of the 
-[[http://catalog.colostate.edu/general-catalog/policies/students-responsibilities/#academic-integrity|CSU 
-General Catalog]] and in the 
-[[https://resolutioncenter.colostate.edu/wp-content/uploads/sites/32/2018/08/Student-Conduct-Code-v2018.pdf|Student 
-Conduct Code]].  At a minimum, violations will result in a grading 
-penalty in this course and a report to the Office of Student 
-Resolution Center. 
- 
- 
-===== Time and Place ===== 
- 
-Class meets every Tuesday and Thursday, 11:00 AM - 12:15 PM, in Computer Science Building 130. 
- 
-The on-line section will be available through Canvas. 
- 
-===== Prerequisites ===== 
- 
-CS440 with a grade of C or better, and some experience with python. 
- 
-===== Textbook ===== 
- 
-There are no required text books for this course.  Readings may be assigned from the following on-line books. 
- 
-[[http://www.labri.fr/perso/nrougier/from-python-to-numpy/|From Python to Numpy]] by Nicolas P. Rougier  
- 
-[[http://www.deeplearningbook.org/|Deep Learning]] by Ian Goodfellow, Yoshua Bengio, and Aaron Courville 
- 
-[[http://incompleteideas.net/book/the-book.html|Reinforcement Learning: An Introduction]], by Richard Sutton and Andrew Barto, 2nd edition 
- 
-===== Instructors ===== 
- 
-These hours and GTA are not current and will be updated! 
- 
-^    ^  ^  Office Hours   ^ 
-^ Chuck Anderson |  chuck.anderson@colostate.edu  |  Zoom meetings\\ Tuesdays/Thursdays: 9:00 - 10:30 am \\  Fill out and submit [[https://forms.gle/P6cWq9zDR8m6BSEr9|this form]] at the start of office hours so Chuck can send you a zoom meeting link.    
-^  GTA: Saira Jabeen  |  saira.jabeen@colostate.edu  |  CS Building Room 120\\ Tuesday : 12pm - 2pm \\ Wednesday : 1pm - 3pm\\ Fill out and submit [[https://forms.gle/76m7ofbY5v7wdcNT8|this form]] at the start of office hours so TA can send you a zoom meeting link.  | 
- 
- 
-===== Grading ===== 
- 
-Your grade for this course will be based on about six assignments, each 
-of which will require the submission of a jupyter notebook that 
-includes text descriptions of your methods, results and conclusions 
-and the python code for defining machine learning algorithms, loading 
-data and applying your algorithms to the data.  Each notebook will be 
-graded for correct implementation and results, thorough discussion of 
-your code and observations of results, and good organization, grammar 
-and spelling. 
-We might have quizzes, but we will not have exams. 
- 
-A final semester project of your own design will be required.  The grade on the project will have as much weight as two to three assignments. 
- 
-/*** 
-**Since we dropped the lowest assignment grade, too much weight will be applied to the final project.  Considering this, your final semester grade will be calculated as a weighted average of your four highest assignment grades average plus your project proposal and report scores, with respective weights of 0.72 (= 4 * 0.18), 0.04 and 024.  So the formula will be  0.72 a + 0.04 prop + 0.24 proj, where a is the average of your highest assignment scores, prop is your proposal score, and proj is your project score. 
-**  In other words, your four best assignments determine 72% of your grade, your project report determines 24% of your grade, and your proposal determines 4% of your grade. 
-***/ 
- 
- 
-Semester letter grades will include plus and minus grades.  Assume 
-standard ranges of numerical grades will be used.  Ranges might be 
-shifted a little lower, depending on the grade distribution at the end 
-of the semester, but they will not be raised. 
- 
-Some assignments will include extra credit points.  These will be 
-accumulated during the semester.  At the end of the semester, if your 
-grade is just below a letter grade cutoff, the extra credit points 
-might push you up to the higher grade.  Each extra credit point is 
-roughly worth 1/2 a percent.  For example, if your grade is 88% and 
-the cutoff or A- is 90%, four extra credit points will bump your grade 
-up to an A-. 
- 
-**Late reports will not be accepted**, unless you make arrangements with the instructor at least two days before the due date. 
- 
-===== COVID-19 ===== 
- 
-All students are expected and required to report any COVID-19 symptoms to the university 
-immediately, as well as exposures or positive tests (even home tests). 
- 
-• If you suspect you have symptoms, or if you know you have been exposed to a positive person or 
-have tested positive for COVID (even with a home test), you are required to fill out the [[https://covid.colostate.edu/reporter/|COVID 
-Reporter]]. 
- 
-• If you know or believe you have been exposed, including living with someone known to be COVID 
-positive, or are symptomatic, it is important for the health of yourself and others that you 
-complete the online COVID Reporter. Do not ask your instructor to report for you. 
- 
-• If you do not have internet access to fill out the online COVID-19 Reporter, please call (970) 491-4600. 
- 
-• You may also report concerns in your academic or living spaces regarding COVID exposures 
-through the COVID Reporter. You will not be penalized in any way for reporting. 
- 
-• When you complete the COVID Reporter for any reason, the CSU Public Health Office is notified. 
-Students who report symptoms or a positive antigen test through the COVID Reporter may be 
-directed to get a PCR test through the CSU Health Network’s medical services for students. 
- 
-For the latest information about the University’s COVID resources and information, please visit the [[https://covid.colostate.edu/|CSU 
-COVID-19 site]]. 
  
syllabus.txt · Last modified: 2023/09/06 15:22 by anderson