Artificial Intelligence

A tantárgy neve magyarul / Name of the subject in Hungarian: Mesterséges intelligencia

Last updated: 2015. február 17.

Budapest University of Technology and Economics
Faculty of Electrical Engineering and Informatics
Engineering Information Systems
Course ID Semester Assessment Credit Tantárgyfélév
VIMIA313   3/1/0/v 5 1/1
3. Course coordinator and department Dr. Dobrowiecki Tadeusz Pawel,
Web page of the course https://portal.vik.bme.hu/kepzes/targyak/VIMIA313/
4. Instructors Dr. Tadeusz Dobrowiecki, MIT
5. Required knowledge matemathical logic, probability, computing science basics
6. Pre-requisites
Kötelező:
(TárgyEredmény( "BMEVISZA213" , "aláírás" , _ ) = -1
VAGY
TárgyEredmény( "BMEVISZAB01" , "aláírás" , _ ) = -1
VAGY
TárgyEredmény( "BMEVIMA2207" , "aláírás" , _ ) = -1
VAGY
TárgyEredmény( ahol a TárgyKód = "BMEVIMA2607", ahol a Típus = "JEGY", ahol a Ciklus = tetszőleges, ahol a KépzésKód = tetszőleges) >= 2
VAGY
( TárgyEredmény( ahol a TárgyKód = "BMETE911708", ahol a Típus = "JEGY", ahol a Ciklus = tetszőleges, ahol a KépzésKód = tetszőleges) >= 2 VAGY TárgyEredmény( "BMETE911708" , "felvétel" , _ ) >0)
VAGY
Szakirány( ahol a SzakirányKód = "KIEGI", ahol a Ciklus = "2006/07/1")
VAGY
Szakirány( ahol a SzakirányKód = "KIEGIBSC", ahol a Ciklus = "2007/08/1")
VAGY
Szakirány( ahol a SzakirányKód = "FVIszgépek", ahol a Ciklus = "_")

VAGY Training.Code=("5NAA78RESZ")

VAGY
EgyenCsoportTagja("Brazil 2015-16-1_erk") )



ÉS NEM ( TárgyEredmény( "BMEVIMIAC00" , "jegy" , _ ) >= 2
VAGY
TárgyEredmény("BMEVIMIAC00", "FELVETEL", AktualisFelev()) > 0)

ÉS Training.Code=("5N-A8")

A fenti forma a Neptun sajátja, ezen technikai okokból nem változtattunk.

A kötelező előtanulmányi rendek grafikus formában itt láthatók.

Ajánlott:
TárgyEredmény( "BMEVISZA213" ,  "aláírás" , _ )  >0
VAGY
TárgyEredmény( "BMEVIMA2207" ,  "aláírás" , _ )  >0
 VAGY
 TárgyEredmény( ahol a TárgyKód = "BMEVIMA2607", ahol a Típus = "JEGY", ahol a Ciklus = tetszőleges, ahol a KépzésKód = tetszőleges) >= 2
 VAGY
( TárgyEredmény( ahol a TárgyKód = "BMETE911708", ahol a Típus = "JEGY", ahol a Ciklus = tetszőleges, ahol a KépzésKód = tetszőleges) >= 2 VAGY  TárgyEredmény( "BMETE911708" ,  "felvétel" , _ )  >0)
 VAGY
 Szakirány( ahol a SzakirányKód = "KIEGI", ahol a Ciklus = "2006/07/1")
 VAGY
 Szakirány( ahol a SzakirányKód = "KIEGIBSC", ahol a Ciklus = "2007/08/1")

A fenti forma a Neptun sajátja, ezen technikai okokból nem változtattunk.

A kötelező előtanulmányi rendek grafikus formában itt láthatók.

7. Objectives, learning outcomes and obtained knowledge The objective of the course is to provide a short but exigent presentation of the field of artificial intelligence in tree main steps: (1) expression of intelligent behavior by computational models; (2) analysis and application of formal methods and heuristics used in artificial intelligence; (3) methods and problems of practical applications.

 Obtained skills and expertise:

 The students satisfying the course requirements will be able to (1) understand and study a new way of computer usage; (2) develop efficient algorithms for computational problems; (3) understand the limits of current information and computation technologies; (4) to intellectually perceive the central role of algorithms in information processing systems.

 

8. Synopsis Agent paradigm: Intelligent system and its environment. Formal modeling and solving of complex problems within agent paradigm. Comparing problem solving methods (search strategies). Heuristics for reducing complexity. Knowledge intensive approach and complexity. Experimenting with the scheduling problems: modeling within the paradigm and solving with the search algorithms. Planning: Planning as a tool of problem solving. Basic representations for planning. The basics of the modern planning algorithms. Hierarchical and conditional planning. The question of the resource constraints. Integrated planning and execution. Experimenting with the assembly problems: developing plans taking into account various problems of increasing complexity. Knowledge intensive systems. Formal representation and manipulation of knowledge. Logic based methods. Using first order logic to describe problems and to compute solutions. The functioning of rule-based systems. Inference methods for uncertain knowledge. Probabilistic inference systems. Representing vague meaning with fuzzy sets. Experimenting with the diagnostic problem with knowledge of different levels of uncertainty, using suitable methods, or experimenting with building a fuzzy system (rule-based language, fuzzy software packages, etc.). Learning. Learning within agent paradigm. Inductive logical learning (decision trees, learning general logical expressions). Learning in neural and Bayesian networks. Reinforcement learning. Genetic algorithms and evolutionary programming. Experimenting with multiple learning problems, using suitable software packages.

 

9. Method of instruction Lectures
10. Assessment

a. During the term:

One midterm exam (in a time point different from lectures), which can be made up on the last week of the term. The required minimum is 40% (20 points). Half of the points of a valid midterm exam adds to the final score.

On home work assignment to be down and uploaded from a dedicated assignment server. Further scheduling is detailed on the server. Assignment qualification is „not passed" (0 points), or „passed" (10-25 points). Assignments points add to the final score.

The subject is acknowledged with a minimum level midterm exam (40%) and a "passed" assignment.

b. During the examination session:

Written exam, minimal level is 40% (20 points). The exam can be conditioned on special control question before the rest of the exam is corrected.

Qualification:  midterm exam - max. 50 points, 40% is the required minimum, to the final score half of the points of a valid exam is added (i.e. min. 10, max. 25 points), exam - max. 50 points, 40% is the required minimum (i.e. 20 points). Assignment yields 10-25 points.

Final qualification: exam points + half of the points of a valid midterm exam + points of a valid assignment.

Scoring: from 40 satisfactory, from 55 average, from 70 good, from 85 excellent.

c. Pre-exam

On demand a preliminary exam can be arranged simultaneously with the reinstating of the midterm exam. (i.e. only those students can take part in the pre-exam who passed the midterm exam earlier). The exam can be conditioned on special control question before the rest of the exam is corrected.

11. Recaps

Acc. to the Exam Code of the Faculty.

The assignment can be uploaded without charge until Wednesday of the reinstate week.

13. References, textbooks and resources Russell and Norvig: Artificial Intelligence: Modern Approach, Prentice Hall; 1st edition, 1995
14. Required learning hours and assignment
Kontakt óra60
Félévközi készülés órákra28
Felkészülés zárthelyire12
Házi feladat elkészítése25
Kijelölt írásos tananyag elsajátítása 
Vizsgafelkészülés25
Összesen150
15. Syllabus prepared by Dr. Tadeusz Dobrowiecki, MIT