Till KTH:s startsida Till KTH:s startsida

Visa version

Version skapad av Patric Jensfelt 2015-07-12 16:16

Visa < föregående | nästa >
Jämför < föregående | nästa >

Course PM

Introduction

This course gives a broad overview of the problems and methods studied in the field of artificial intelligence.

Please respect the code of honour.

Intended learning outcomes

After completing this course the student should be able to

  1. recall and apply basic concepts in artificial intelligence

  2. solve problems from the AI domain with limited resources in the form of time and computations

  3. formulate and address an AI related scientific problem

  4. demonstrate an insight into the risks of AI and its role in society

  5. present work in writing and orally

so that the student can

  • make use of methods from artificial intelligence in the analysis, design and implementation of computer programs in academic as well as industrial applications

  • in an appropriate way present results and solutions.

Crew 

  • Lecturer and course responsible
  • Teaching assistants (TA)
    • Johannes A. Stork
    • Akshaya Thippur
    • Kaiyu Hang

Self study lectures

The student body of the course has drastically different background knowledge. Since the course started we spent time introducing basic concepts in search and probabilistic reasoning. Starting this year, to be able to use the time we have in the classroom to introduce concepts which are new to must rather than only some we will provide some material for self studies. The initial two self study lectures covers two things that all CS students at KTH will already know about and are not directly related to the course material but which you need to know about.

Content Chapters Downloads 
Code of honour (QUIZ) N/A
How to use the code submission system Kattis N/A
Basic search (QUIZ) 3
Basic probabilistic reasoning (QUIZ) 13

Lectures

The table below gives a rough overview of the lectures. The lecture notes will be posted in conjunction with the lecture. The exact content of each lecture is only tentative and may be adapted along the way.

The chapters refers to the course book "Artificial Intelligence: A Modern Approach" (3rd Edition) by Stuart J. Russell and Peter Norvig.

In the table below the means of examination has been indicated for each lecture. 

 # Content Chapters Downloads 
L1  Introduction 1-2 
L2  Search (HW1, HW2, QUIZ), Games (HW1, QUIZ) 3,4 
L3  CSP (QUIZ) 3-6
L4  Ethics (HW3)
L5  Guest lecture: Gabriel Skantze
Natural Language Processing (PROJECT)
22-23
L6  Probabilistic reasoning, Bayesian Networks,
Hidden Markov Models (QUIZ, HW2)
13-15 
L7  Hidden Markov Models (QUIZ, HW2) 13-15 
L8  Logic and Representation of Knowledge (QUIZ) 10-11  
L9  Planning (QUIZ) 7-9, 12
L10  Making decisions (MDP + POMDP) (QUIZ) 16-17
L11  Guest lecture: Stefan Carlsson
Deep Learning  (QUIZ)
-
L12  TBD
L13  Robotics and computer vision
Research at CVAP What we do and how we kick ass!
24-25

Exercises 

Exercises/tutorials are carried out in smaller groups and allow for more interaction between students and teachers. The exercises also help bridge the gap between what is discussed in the lectures and the assignments but adding some more practical advice. 

# / Week Tutorial Title Content Downloads 
1 / w36  Search

Search

2 / w37 Games Games: minimax, alpha-beta, 
heuristics, testing 
3 / w39  HMM1 HMM: core concepts and algorithms: 
forward pass, backward pass, 
baum-welch; solving examples 
4 / w40  HMM2 HMM: Viterbi algorithm, HMM examples, 
Real world HMM problems, 
HMM problem decomposition 
TBD TBD 

Additional material

The material below is not directly related to AI but we believe that the content is something that students of computer science should know about and which will help you in your work.

Content Downloads, Links, etc
Piping (mainly for HW1: Checkers)
Versioning
Coding tips

Help Sessions

We offer help sessions which  usually in room 22:an (304), at Teknikringen 14. The KTH webpage has a map that can show you the way there. On some occasions the help sessions have to be moved to a different room. To know when we change the room, read the information page about help sessions.

Examination and grading

The examination consists of completing quizzes, homework assignments (individual) and a projects (in groups). 

To receive a passing grade on the course a student needs to pass all quizzes, the home work assignment (HW1, HW2, HW3) as well as the requirements for the project. The project has to be completed in groups.

Each homework assignment and the project will be given a numeric score which is summed up. 

  Max points 
Quizzes P/F
HW1  25
HW2  35
HW3 P/F
Project  40

The final grade, A-F, is given according to

  • A: >=85 
  • B: >=75 
  • C: >=65 
  • D: >=55 
  • E: >=40

NOTE: All homework assignments and project should be completed in English 

For all examinations, we use the CSC code of honour.

Homework

This course gives a broad overview of the field of AI. The homeworks are intended to give the student a chance to work with the material a bit more hands-on.

There will be 2 homework assignments and an initial basic programming test handed out during the course. Please pay attention to the dates for handing them in as we will be strict with the deadlines! 

There will be two deadlines for HW1 and HW2. Assignments handed in before the first deadline, the bonus deadline, are rewarded with an additional 2 points (assuming you meet the minimum requirements for the corresponding assignment). Submission after the second deadline are limited to getting a maximum of the minimum required number of points. You submit electronically (to kattis) and you are allowed to submit as many times as you want and for both deadlines if you want and the best result will count. Note that the bonus points are only added to the score on assignments handed in before the bonus deadline. That is, if you get 5 points at the first deadline and 6 points at the second you score would be 5+2=7 and not 6+2. 

Please ask questions about the homeworks via this portal or at one of the help sessions.

Project

The project offers you a chance to practice team work and work on a slightly larger problems that require you to work together. Being able to work in a group is an instrumental skill in most jobs both in academia and industry. You will be required to write a report, make a presentation and review another group's report and act as opponents at their presentation. The score on the project is based on all of these parts, ie not only your "end product").

The project work should be carried out in groups of 4 people. You are free to form your own groups. You define the group in the course portal. People that have not formed groups by the deadline will be assigned groups.

NOTE: You cannot be part of a group until you passed the BPT 

NOTE: You will be given a deadline to form groups. If you want to be in a certain group, make sure to form the group before the deadline. If you are not a member of a team (enough if team members have invited you to be considered to be part of the team) after that deadline you have forfeited your ability to chose group and will be placed in a group. 

Please ask questions about the project here or on one of the help sessions.

Consultation

If you have questions or problems of organizational or formal character regarding this course, please do not contact the professor directly. Instead make use of the consultation time on Monday, 12:15 pm - 1 pm, Computer Vision and Active Perception Lab, Teknikringen 14, Plan 7, Room 721. Take the stairs to Plan 7 and ring the doorbell or call someone to send the elevator down.