Artificial Intelligence and Computer Vision - 2018/2019 Electronic and Computer Engineering Faculty of Electronics

NOTE:
Proposed exam dates: January 31st and February 5th, 2019, 6-8 pm.
Please reserve these dates.
See the exam section for more information.

Lecture topics and notes

These notes are under copyright. They can be used only for anybody's private purposes, and cannot be distributed or published, for example by copying and making available from other Web pages, or in any other way.

no	lecture	slides
1	Introduction. Artificial intelligence.
	Introduction. Computer Vision.
2	Searching for solutions. Uninformed search strategies.
3	Image sampling. Theory and hardware implementations.
4	Informed search strategies. Heuristic evaluations functions.
5	Splines and interpolation. Demosaicking.
6	Local search algorithms. On-line search agents. Searching in games. Minimax algorithm.
7	Orthogonal series and approximation.
8	Knowledge-based agents. Knowledge representation using propositional calculus and predicate calculus.	ArtInt2e Prolog
9	Noise in imaging. Anscombe transform.
10	Logic programming. Horn clauses. Prolog
11	Convolution and image filtering.
12	Probabilistic representation. Conditional probability. Bayes' rule. Bayesian networks.
13	Shape detection, object tracking.
14	Action planning.
15	Scene reconstruction, motion capture and gesture recognition.

Literature

1. S.J.Russell, P.Norvig, Artificial Intelligence A Modern Approach (Third Edition), Prentice-Hall, 2010, WWW
2. Forsyth, Ponce, Computer Vision A Modern Approach, Second Edition, Prentice-Hall, 2011
3. Szeliski, Computer Vision: Algorithms and Applications, Springer, 2011
4. Prince, Computer Vision: Models, Learning, and Inference, Cambridge 2012

1. Artificial intelligence courses with similar programs:
   • University of Waterloo, Canada, Introduction to Artificial Intelligence, Fall 2012, Pascal Poupart
   • M.I.T., Electrical Engineering and Computer Science, 6.034 Artificial Intelligence, Spring 2005, Tomás Lozano-Pérez, Leslie Kaelbling
   • M.I.T., Electrical Engineering and Computer Science, 6.825 Techniques in Artificial Intelligence, Fall 2002, Tomás Lozano-Pérez, Leslie Kaelbling

Final exam

The written examination schedule:

The scope of the exam covers all the lecture and project class program, see the detailed list of topics for this exam.

The results of the written exam will be made available through the grandson test results form.

“Grandson” tests

1. Tests are written, 3-minutes long, and can occur at any time during the lecture.
2. The scope of the test will be the current lecture, with a possible overlap of the preceding lecture.
3. This is a closed-book test. No books, notes, or computers can be used.
4. Calculators are permitted. During some tests, simple numerical calculations will be necessary. A cell phone, a calculator watch, or a PDA, will be allowed. But hand calculations is also possible.
5. Tests are graded from 1 to 3 points, with 1 point given for a blank page turned in.
6. No-show means 0 points. No re-taking and no excuses.
7. The final “grandson” test score will be computed by dropping the single highest score and the single lowest earned score. 0 points result for absence is never dropped.

The Android app

Final exam waiver

The grades from the grandson test results will be counted towards the final exam as follows:

The Lab class

The schedule of the lab assignments is given below. Each assignment will be explained and discussed in class at the time of its start.

The lab assignments must be worked out individually. It is not allowed to share solutions with colleagues, or submitting results which are not the author's own. It is allowed to use any published resources, as long as they are properly credited and referenced in the report.

A written PDF report must be prepared for each assignment and turned in through the Moodle system. The detailed requirements for each report are given in the Moodle system, along with the grading criteria.

Grading the lab class

The lab assignment schedule

	subject	description	tools
1.	Introduction to problem solving by searching		AI Space
2.	Road navigation by graph searching
3.	Heuristic search for games: 3D tic-tac-toe
4.	Representing knowledge as logical facts: Prolog
5.	Probabilistic knowledge representation: the Bayesian Belief Networks

The Project class

Separate reports must be prepared for both assignments. Each report has to be a single-page HTML document. It must be possible to print the report. It can contain images, or even multimedia content, like applets (it is OK if the report does not print out completely). All the reports will be published by the instructor on the course Web page, so they have to be prepared accordingly. In particular, the following requirements are ESSENTIAL:

1. the report must have a heading stating: the title of the project, the name of the author, the date, and a declaration that the report describes a project done to fulfill the requirements for this course,
2. the report must conform to some standard of HTML, ie. must successfully verify against the standard given in the DOCTYPE declaration,
3. the report must be spell-checked before submitting
4. the report must contain a list of all source materials, and programming tools used,
5. the report MUST NOT contain links allowing to download source codes from the report home server.

The report should describe the goal of the project, the methods used, the results achieved (well edited examples very welcome), the evaluation of these results, and some general conclusions or remarks. The quality of the report will be a significant factor in grading the project.

After preparing the report it has to be installed as the student's Web page on the departmental server.

“Grandson” test results