Instructor | Lectures | Literature | Examination | Results | Project | Schedule
logo PWr

Artificial Intelligence and Machine Learning - 2024

Embedded Robotics
Department of Cybernetics and Robotics
Faculty of Electronics, Fotonics, and Microsystems



Lecture topics and notes

The following table contains the titles of all the lectures, and links to the lecture notes in PDF format. Lecture notes are provided for the convenience of the students, so it is not necessary to take notes in class. Please note that they are no substitute for textbooks, and other study materials. Further links to other literature are provided in the Literature section.

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.

notopicslides
1
2
Searching in the state space
Searching in games
Searching in constraint satisfaction problems
PDF
3 Logic based methods PDF
4 Logic programming in Prolog PDF
5 Probabilistic representation: Bayesian networks PDF
6 Making simple decisions: utility functions PDF
7 Making complex decisions PDF
8 Reinforcement learning algorithms PDF
9
10
11
Machine learning: basic concepts and classification algorithms PDF
12 Unsupervised learning PDF
13
14
Neural networks and deep learning PDF
15 Computational theory of learning PDF


Literature

Textbooks:
  1. S.J.Russell, P.Norvig, Artificial Intelligence A Modern Approach (Third Edition), Prentice-Hall, 2010, WWW
  2. T.Mitchell, Machine Learning, McGraw Hill, 1997, WWW
Internet resources:
  1. Artificial intelligence courses with similar programs:

  2. Polish language courses:

  3. Search methods:

  4. Textbooks and tutorials on Prolog:

  5. Systems for creating probabilistic belief networks:

  6. Internet repositories of statistical data:
    UCIKnowledgeDiscovery UCI Knowledge Discovery in Databases Archive
    UCIMLRepository UCI Machine Learning Repository
    CMUStatLibDatasets CMU StatLib Datasets Archive

  7. Markov decision processes and reinforcement learning:

  8. Supervised and unsupervised machine learning:

  9. Neural networks and deep learning:


Final exam

Passing and obtaining credit in the lecture class requires successfully passing a written examination at the end of the semester. The date of this examination will be negotiated and announced later. At the end of the semester a list of topics for the exam will also be published, and example problems will be presented and discussed.

The time and venue of the written examination will be announced during the first part of the semester.

Final exam waiver

All lectures will include short (5-10 minutes) written tests. Obtaining at least 60% of the total score on these tests earns an exemption from the final exam with a grade of 4.0 and up. Results below 60% give nothing.

The final test score will be computed by dropping the single highest test score and the single lowest earned score. 0 points results for absence are never dropped.

The scores from the tests will be interpreted as follows:

points[%] 60.0073.3386.66
grade 4.0 4.5 5.0

The tests will be administered in two variants: either a theoretical true/false/do not know questions test, the so called “Hash Test”, or a computational test, the so-called “Grandson Test”. These tests have different mechanics described below.

The “Grandson Test” rules

The “Grandson” tests have a single question related to the current lecture's material. They are graded from 1 to 4 points, with 1 point given for a blank page turned in.
No-show yields 0 points. No re-taking and no excuses.

Read the details of the “Grandson Test” mechanics.

The “Hash Test” rules

The Hash Test is a timed test with sixteen yes/no/I don't know questions. It can be written using an Android smartphone, or simply on paper. In either case, you cannot use any source materials, notes, materials from the Internet, etc.
The test can only be taken in person, in the lecture hall, during the normal test time.

Read the details of the “Hash Test” mechanics.

Test results

The following form can be used to find your test results. The spelling of first and last names are exactly as entered in the USOS system. Non-Latin letters (with accents, etc.) need to be spelled exactly as in USOS. (However, for the project class results, use the spelling of your name from the eportal system.) Additionally, multiple last names must be joined here with underscores, like de_la_Vega.
IMPORTANT: temporarily, only the single first name should be used to retrieve test results. Use your first name spelling as entered in the USOS system. Do not use your middle name, even if it appears in USOS.
First name(s):
Last name: Compute modulo 16:
Student number:


The Project class

The project class will consist of a series of assignments. The necessary and sufficient condition to obtain a passing grade for the project class is to successfully and timely complete (obtain a positive point credit) all the project assignments, except at most one assignment. Missing one assignment results only in forfeiting credit for that assignment. Missing more than one assignment results in failing the project class.

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

The 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.

Either a written PDF report, or the code worked out, or both, must be turned in through the Moodle system. The detailed submission requirements for each assignment are given in the Moodle system, along with the grading criteria. However, the details of the projects are only provided here.

Grading the project class

points(%) 50.0060.0070.0080.0090.00
grade 3.0 3.5 4.0 4.5 5.0

The Project assignment schedule

subjectdescr.toolsstartduedeadline
1.Heuristic search - checkers clk Checkers program + Java March 6March 26Apr 2
2.Logical reasoning - wumpus clk
Jovolog simulator + Prolog March 20April 16April 23
3.Bayesian networks modeling and decision making clk many available, see description April 3April 30May 7
4.Markov decision problems and reinforcement learning clk
programming language to choose: Python3, Java, C/C++
Russel+Norvig 4x3 world data file
assignment 4x4 world data file
April 17May 14May 21
5.Classifier machine learning clk Python3 scikit, many other libs
data: text database
May 8May 28June 4
6.Unsupervised learning clk Python scikit, many other libs
data: image database
May 22June 11June 18


Instructor | Lectures | Literature | Examination | Results | Project | Schedule
Visit count since September 20, 2011: counter
Updated: Monday, 11-Mar-2024 19:20:56 CET   Valid XHTML 1.0 Transitional! Valid CSS!