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

Artificial Intelligence and Machine Learning - 2018/2019

Embedded Robotics
Department of Cybernetics and Robotics
Faculty of Electronics



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.

nolecturematerials
slidesprintout
1 Introduction to artificial intelligence and machine learning PDF PDF 2x1 PDF 4x1 PDF 6x1
2
3
4
Searching in the state space
Searching in constraint satisfaction problems
Searching in games
PDF PDF 2x1 PDF 4x1 PDF 6x1
5 Logic based methods PDF PDF 2x1 PDF 4x1 PDF 6x1
6 Logic programming in Prolog PDF PDF 2x1 PDF 4x1 PDF 6x1
7 Probabilistic representation: Bayesian networks PDF PDF 2x1 PDF 4x1 PDF 6x1
8 Making simple decisions PDF PDF 2x1 PDF 4x1 PDF 6x1
9 Making complex decisions PDF PDF 2x1 PDF 4x1 PDF 6x1
10 Reinforcement learning algorithms PDF PDF 2x1 PDF 4x1 PDF 6x1
11
12
13
14
Machine learning: basic concepts and algorithms PDF PDF 2x1 PDF 4x1 PDF 6x1
15 Computational theory of learning PDF PDF 2x1 PDF 4x1 PDF 6x1


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. Rule-based representations - CLIPS:

  6. Systems for creating probabilistic belief networks:

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

  8. Machine learning:

  9. Reinforcement learning:


Final exam (pol. kolokwium)

Passing and obtaining credit in this course requires successfully completing the project class for the course, and successfully passing a written examination at the end of the semester. The date of the written examination will be determined about half way through the semester, at which time the list of topics will also be announced, and example problems presented and discussed. The final course grade is computed from the project class score (weight 0.6) and the exam score (weight 0.4) rounded to the closest nominal grade.

The time and location of the written examination will be announced towards the end of the semester.

“Grandson” tests

There will be short, single question tests at all lectures. The rules:
  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

Android smartphone owners may find this simple application useful when writing the “grandson” tests in class: Group number calculation app
If you do not have an Android smart phone, don't worry. You may be able to use a colleague's phone, or you can do without it.

Final exam waiver

A minimum of 60% result from the “grandson” tests gives a waiver from the final exam with the grade of 4.0. Results below 60% from the “grandson” test give nothing.

The grades for the grandson test results will be interpreted as follows:

points[%] 60.0073.3386.66
grade 4.0 4.5 5.0

“Grandson” test results

Use the following form to find your “grandson” test results. The spelling of first and last names are exactly as entered in the Edukacja system. Non-Latin letters (with accents, etc.) need to be spelled exactly as in Edukacja. (However, for the project class results, use the spelling of your name from the eportal system.) Additionally, multiple first and/or last names must be joined here with underscores, like Manuel_Antonio, or de_la_Vega.
First name: Last name:
Student number:


The Project class

The project class will consist of a series of assignments. The initial series are “small” assignments, which are connected to lectures. Then there is an individual project - the “big” assignment. The subject can be anything, but must be approved by the instructor. The “big” assignment is optional, in the sense, that another series of “small” assignments can be done instead of it.

A 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 assignments within the selected option, except at most one “small” assignment. Missing one “small” assignment results only in forfeiting the credit for that assignment. Missing more than one assignment results in failing the project class.

The “small” assignments

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

“Small” 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.

The “big” project

The detailed requirements for the “big” assignment option are given in a separate specification.

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.Startup assignment - semantic networks, ontologies clk Protégé Oct.4Oct.18Oct.25
2.Heuristic search - checkers clk Checkers program + Java Oct.18Nov.8Nov15
3.Logical reasoning - wumpus clk
Jovolog simulator + Prolog Nov.8Nov.22Nov.29
4.Bayesian networks modeling and decision making clk many available, see description Nov.22Dec.6Dec.13
5.Markov decision problems and reinforcement learning clk any programming language Dec.6Dec.20Jan.10
6.Classifier machine learning clk WEKA, RapidMiner, others Dec.20Jan.17Jan.24


Instructor | Lectures | Literature | Examination | Results | Project | Schedule
Visit count since September 20, 2011: counter
Updated:    Valid XHTML 1.0 Transitional! Valid CSS!