CSCI 4155/6505 Machine Learning (with Robotics) 2012
Instructor: Dr. Thomas Trappenberg
Teaching Assitant: Paul Hollensen
Office: Room 4216 in Mona Campbell Building on Coburg RD (main) and Room 313 in Goldberg building (office hour)
Office hour: Tuesdays 3-4pm, Goldberg Building, Room 313
This course discusses learning theories and demonstrates these strategies with robots. The topics include supervised learning, in particular maximum likelihood estimation in stochastic models and statistical learning theory including support vector machines, unsupervised learning which includes generative models, expectation maximization, and Boltzmann machines, and reinforcement learning including Markov decision processes and temporal difference learning. We will also discuss some basic computer vision, control theory, localization and mapping, and path planing. Toward the end of the course we will discuss some cognitive robotics.
Some emphasis will be given to try the concepts with mobile robots based on the Lego NXT robotics hardware. We will be using a Python programming environment that will be introduced at the start of the course. We will be using some mathematical descriptions and thus need familiarity with concepts such as basic calculus and specifically probability theory. The basic probability theory required in this course will be reviewed, and other tutorials can be given if requested.
There is no required text for the course. Course notes will be posted on the course web site. But I recomment the following additional reading:
Christopher Bishop, Pattern Recognition and Machine Learning, Springer 2006.
Ethem Alapydin, Machine Learning, MIT Press, second edition, 2011
Lecture notes by Andrew Ng: http://www.stanford.edu/class/cs229/materials.html and http://www.stanford.edu/c
Russell and Norvig, Artificial Intelligence: A modern approach, Prentice Hall
Richard Sutton and Andrew Barto, Reinforcement Learning: An Introduction, MIT press, 1998.
S. Thrun, W. Burgard, and D. Fox, Probabilistic Robotics, MIT Press 2005.
CSCI 4155: 40% Assignments, 40% Tests, 20% Project
CSCI 6505: 25% Assignments, 30% Tests, 10% Paper presentation, 35% Project
Grades will be assigned using the letter grade scale as defined in section 17.1 of Dalhousie Academic Calendar.
Sept 4: First three chapters of the manuscript
Sept 25: Chapter 4 on supervised learning
Sept 27: Note on Assignment 3. I posted the Bayes net program under the `Resources' below. You can use this to verify your answer to question A3.4, but you need to show how to calculate this by hand. You can scan your handwritten page if it is to cumbersome for you to write out the formulas in a text processor.
Oct 9: Chapter 5 on unsupervised learning now online.
Oct 15: Chapter 6 on reinforcement learning now online.
Oct 30: A short Chapter 7 on some computer vision. See also Sebastian Thrun's videos from his introductory AI class.
Oct 31: Slides for Localization & Bayes Filtering (Chapter 8)
Assignments will be posted on the web in the table below. The assignment A0 is an example, and the file A0answers contains the answers to these questions.
|Sep 6||Intro, Python (Ch 1)||A1|
|Sep 11||Python, Minimization, Robotics (Ch 2)|
|Sep 13||Robotics, control theory (Ch 2)||A2|
|Sep 18||Probability (Ch 3)|
|Sep 20||Probability/ motion and sensor models (Ch 3)||A3 (extended to Monday 4pm)|
|Sep 25||Supervised learning (Ch 4)|
|Sep 27||Supervised learning (Ch 4)|
|Oct 2||Supervised learning (Ch 4)|
|Oct 4||Supervised learning (Ch 4)||Q1||A4, A4Q1_data, A4Q2_train_data, A4Q2_train_labels, A4Q2_test_data|
|Oct 9||Unsupervised learning (Ch 5)|
|Oct 11||Unsupervised learning (Ch 5)||A5|
|Oct 16||Unsupervised learning (Ch 5)|
|Oct 18||Reinforcement Learning (Ch 6)||Q2|
|Oct 23||Reinforcement Learning (Ch 6))||Chain_policy_iteration.py|
|Oct 25||Reinforcement Learning (experiment)||A6|
|Nov 30||Computer Vision (Ch 7||skimage_demo.py|
|Nov 1||Computer Vision (Ch 7)/ Localisation and Mapping (Ch 8)|
|Nov 6||Localisation and Mapping (Ch 8)||A7|
Planning (Ch 9)
|Nov 13||STUDY DAY|
|Nov 15||Planning (Ch 9)|
|Nov 20||Cognitive Robotics (Ch 10)|
|Nov 22||Paper presentation / Project|
BayesNet program with BurglaryEarthQuake example
Chris Bishop: ICML 2011 Keynote talk with title "Embracing Uncertainty: Applied Machine Learning Comes of Age".
TED talk by Sebastian Thrun
A demonstration program of the A* search algorithm, written by Bob Sturm.
RBM demo from Geoff Hinton
RBMletter example (zip file) in matlab. Python version: RBM_example.py and pattern1.txt
A brief guide to writing a scientific paper
(Based on the sample statement provided at http://academicintegrity.dal.ca. Written by Dr. Alex Brodsky.)
Please familiarize yourself with the university policy on Intellectual Honesty. Every suspected case will be reported.
At Dalhousie University, we respect the values of academic integrity: honesty, trust, fairness, responsibility and respect. As a student, adherence to the values of academic integrity and related policies is a requirement of being part of the academic community at Dalhousie University.
What does academic integrity mean?
Academic integrity means being honest in the fulfillment of your academic responsibilities thus establishing mutual trust. Fairness is essential to the interactions of the academic community and is achieved through respect for the opinions and ideas of others. Violations of intellectual honesty are offensive to the entire academic community, not just to the individual faculty member and students in whose class an offence occurs. (see Intellectual Honesty section of University Calendar)
How can you achieve academic integrity?
• Make sure you understand Dalhousies policies on academic integrity.
• Give appropriate credit to the sources used in your assignment such as written or oral work, com- puter codes/programs, artistic or architectural works, scientific projects, performances, web page designs, graphical representations, diagrams, videos, and images. Use RefWorks to keep track of your research and edit and format bibliographies in the citation style required by the instructor (http://www.library.dal.ca/How/RefWorks)
• Do not download the work of another from the Internet and submit it as your own.
• Do not submit work that has been completed through collaboration or previously submitted for another assignment without permission from your instructor. • Do not write an examination or test for someone else.
• Do not falsify data or lab results.
These examples should be considered only as a guide and not an exhaustive list.
What will happen if an allegation of an academic offence is made against you?
I am required to report a suspected offence. The full process is outlined in the Discipline flow chart, which can be found at: http://academicintegrity.dal.ca/Files/AcademicDisciplineProcess.pdf and in- cludes the following:
1. Each Faculty has an Academic Integrity Officer (AIO) who receives allegations from instructors.
2. The AIO decides whether to proceed with the allegation and you will be notified of the process.
3. If the case proceeds, you will receive an INC (incomplete) grade until the matter is resolved.
4. If you are found guilty of an academic offence, a penalty will be assigned ranging from a warning to a suspension or expulsion from the University and can include a notation on your transcript, failure of the assignment or failure of the course. All penalties are academic in nature.
Where can you turn for help?
• If you are ever unsure about ANYTHING, contact myself.
• The Academic Integrity website (http://academicintegrity.dal.ca) has links to policies, defini tions, online tutorials, tips on citing and paraphrasing.
• The Writing Center provides assistance with proofreading, writing styles, citations.
• Dalhousie Libraries have workshops, online tutorials, citation guides, Assignment Calculator, Ref- Works, etc.
• The Dalhousie Student Advocacy Service assists students with academic appeals and student discipline procedures.
• The Senate Office provides links to a list of Academic Integrity Officers, discipline flow chart, and Senate Discipline Committee.
Students may request accommodation as a result of barriers related to disability, religious obligation, or any characteristic under the Nova Scotia Human Rights Act. Students who require academic accommodation for either classroom participation or the writing of tests and exams should make their request to the Advising and Access Services Center (AASC) prior to or at the outset of the regular academic year. Please visit www.dal.ca/access for more information and to obtain the Request for Accommodation – Form A.
A note taker may be required as part of a student’s accommodation. There is an honorarium of $75/course/term (with some exceptions). If you are interested, please contact AASC at 494-2836 for more information.
Please note that your classroom may contain specialized accessible furniture and equipment. It is important that these items remain in the classroom, untouched, so that students who require their usage will be able to participate in the class.