Till KTH:s startsida Till KTH:s startsida

Visa version

Version skapad av Patric Jensfelt 2015-04-10 13:19

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.

Crew 

  • Lecturers
  • Teaching assistants (TA)
    • Johannes A. Stork
    • Akshaya Thippur
    • Kaiyu Hang 

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.

  Date Content Chapters Downloads 
L1  Introduction Agents and search, 
hw+proj intro
1-2 
L2  Search 3,4  lecture02
L3  Search  Games  3-5  lecture03
L4  CSP  lecture04
L5  Probabilistic reasoning  13, 14  lecture05
L6  Bayesian Networks  13-15  lecture06
probabilities_recap
L7  Hidden Markov Models 1  13-15  lecture07
HMM_Tutorial_Mann
HMM_Tutorial_Rabiner 
HMM_Tutorial_Stamp
L8  Hidden Markov Models 2  13-15  lecture08
L9  Logic and Representation of Knowledge  10-11  lecture09 and lecture10.1
L10  Planning  7-9, 12 lecture10.2
L11  Guest lecture: Gabriel Skantze  22-23  -
L12  Project Report Feedback Slides
L13  Making decisions  16-17 lecture13
L14  Robotics, computer vision and machine learning 24-25  lecture14

Exercises 

# / Week Tutorial Title Content Downloads 
1 / w36  BPT Search Admin: Kattis, portal, Hands-on: 
using pipes, version control, tips
Tutorial Slides
2 / w37 Games Games: minimax, alpha-beta, 
heuristics, testing 
Tutorial Slides
3 / w39  HMM1 HMM: core concepts and algorithms: 
forward pass, backward pass, 
baum-welch; solving examples 
Tutorial Slides 

HMM1_Handout_Qs

HMM1_Handout_As

HMM1_Handout_Bolt

HMM1_Handout_Weather
4 / w40  HMM2 HMM: Viterbi algorithm, HMM examples, 
Real world HMM problems, 
HMM problem decomposition 
Tutorial Slides  

HMM2_Handout_Qs

HMM2_Handout_As
Ethics CANCELED 

Help Sessions

We offer help sessions every day of the week (Mon-Fri), usually at 15:00, 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 homework assignments (individual) and a projects (in groups). 

To recieve a passing grade on the course a student needs to pass all home work assignment (BPT, HW1, HW2 HW3/Ethics) 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 
BPT  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.