User Tools

Site Tools


syllabus

Differences

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

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
syllabus [2019/10/15 06:57]
anderson [Grading]
syllabus [2021/05/17 14:53] (current)
anderson [Grading]
Line 3: Line 3:
 ===== Description ===== ===== Description =====
  
-This course covers fundamental and advanced concepts and methods involving deep neural networks for solving problems in data classification, prediction, visualization, and reinforcement learning. Students will learn how to+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,   * read data files of various formats and visualize characteristics of the data,
Line 9: Line 11:
   * develop and apply classification algorithms to classify multivariate data,   * develop and apply classification algorithms to classify multivariate data,
   * develop and apply regression algorithms for finding relationships between data variables,   * develop and apply regression algorithms for finding relationships between data variables,
-  * develop and apply reinforcement learning algorithms for learning to control complex systems, 
-  * write scientific reports on computational machine learning methods, results and conclusions, 
   * use the latest features in python, including jupyter notebooks, and   * 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.   * how to repeat experiments described in on-line tutorials, documentation, and publications in deep learning.
  
-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. +Students will //learn// how to
  
-CS440 is the prerequesite for this course.  HoweverCS445 provides more relevant background for the material in CS545.  Some of the CS445 will be revisited in CS545.  The main difference between CS545 and CS445 is the scale of the assignmentsmore material relates to Pytorch and Tensorflow, and discussions of recent papers in the research literature on deep learning.+  * formulate and derive new algorithms for deep neural networks, 
 +  * develop and apply reinforcement learning algorithms for learning to control complex systems, 
 +  * interpret what deep neural network has learned, 
 +  * investigate the true advantages and limitations of recently developedpopular, 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.
  
-Class meetings will be a combination of lectures by the instructordiscussions of students' questions, and some student presentations in classAll questions are welcomeno matter how simple you think they are; it is always true that someone else has 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.+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 courseplease 
 +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 
 +recommendedwhich is a free download for all platforms.
  
-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 directlyor via our Piazza Discussion boardbut 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+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.
  
-You are expected to be familiar with the [[http://www.cs.colostate.edu/advising/student-info.html|CS Department policy]]  +Class meetings will be a combination of lectures by the instructor, 
-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.  +discussions of students' questions, and some student presentations in 
-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 minimumviolations will result in grading penalty in this course and a report to the Office of Student Resolution Center.+classAll questions are welcomeno matter how simple you think they 
 +are; it is always true that someone else has 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 ===== ===== Time and Place =====
  
-Class meets every Tuesday and Thursday, 8:00 AM 9:15 AM in Room 130 in the CS Building.  Distance-learning students will be able to watch video recordings of lectures through our Canvas web page.+Class meets every Tuesday and Thursday, 12:30 PM 1:45 PM, in Eddy Room 10.   
 + 
 +The on-line section will be available through Canvas.
  
 ===== Prerequisites ===== ===== Prerequisites =====
Line 43: Line 91:
  
 [[http://www.deeplearningbook.org/|Deep Learning]] by Ian Goodfellow, Yoshua Bengio, and Aaron Courville [[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 [[http://incompleteideas.net/book/the-book.html|Reinforcement Learning: An Introduction]], by Richard Sutton and Andrew Barto, 2nd edition
 +
 ===== Instructors ===== ===== Instructors =====
  
 ^    ^  Office  ^  Hours  ^  Contact  | ^    ^  Office  ^  Hours  ^  Contact  |
-^  [[http://www.cs.colostate.edu/~anderson|Chuck Anderson]]  |  Computer Science Building (CSB) Room 444   Tuesday 10 AM - 12\\ Wednesday 1 PM - 3      |  chuck.anderson@colostate.edu\\  970-491-7491 +^  [[http://www.cs.colostate.edu/~anderson|Chuck Anderson]]  |  to be determined     
-^  GTA: Dejan Markovikj  |  CSB 235, Desk 1  |  CS120\\ Tuesday/Thursday 12 - 2 PM  |  dejan.markovikj@colostate.edu   |+ chuck.anderson@colostate.edu\\  970-491-7491 
 +^  GTA: \\ to be determined  |   |  to be determined |
  
  
 ===== Grading ===== ===== Grading =====
  
-Your grade for this course will be based on the assignments, most+Your grade for this course will be based on six to eight assignments, each
 of which will require the submission of a jupyter notebook that of which will require the submission of a jupyter notebook that
 includes text descriptions of your methods, results and conclusions includes text descriptions of your methods, results and conclusions
Line 64: Line 113:
 and spelling.  No quizzes or exams will be given. and spelling.  No quizzes or exams will be given.
  
-Six to seven regular assignments are planned during the semester. In total these will count for 70% of your semester grade. The final assignment is a team project designed by you and at least two classmates and is worth 20% of your semester grade.  10% of your final grade for on-campus students will be based on your in-class presentation made during the final three weeks of the semester.  Your project must include at least two other team members.  The final grade for online students will only be based on assignments. +A final semester project of your own design might be required.  This will be determined prior to the start of the fall semester. If a semester project is required, the grade on the project will have as much weight as two assignments.
- +
-  * 70% regular assignments, from 10% to 13% each  (80% for online students) +
-  * 2% for the project proposal +
-  * 18% for the project written report +
-  * 10% in-class presentation  (only for on-campus students)+
  
-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.+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-.+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. **Late reports will not be accepted**, unless you make arrangements with the instructor at least two days before the due date.
  
syllabus.1571144266.txt.gz · Last modified: 2019/10/15 06:57 by anderson