Course syllabus

Course-PM

MMS131 Introduction to Artificial Intelligence, SP4, 2023 (7.5 hp)

General information

The course is offered jointly by the department of Mechanics and Maritime Sciences (M2) and the Physics department (F). Lectures will be given on-site at the campus, they will not be live streamed. We will upload slides after the lectures so that anyone who is ill can still obtain the material from the lecture. However, students who are not ill should attend the lectures on campus.

Contact details

During the course, we strive to be available as much as possible. You are welcome to ask questions at any time, either in the lectures or via e-mail or telephone. You are always welcome at our offices, but it's a good idea to first check (e.g. via e-mail or telephone) that the person you intend to visit is in the office.

Examiner:

Lecturers:

Teaching assistants:

Course purpose

The course aims to introduce the students to artificial intelligence including, but not limited to, the important subfield of machine learning.

Schedule

The course schedule is given below and can also be found at TimeEdit.

Literature (see section below):

  • AIMA = Artificial intelligence: A modern approach
  • MLNN = Machine learning with neural networks
  • RLAI = Reinforcement learning: An introduction
Day-by-day schedule

Date

Time

Room

Teacher

Content

20230320 Mon.

08:00 – 09:45

HA4

MW

Course introduction, general overview of course topics

20230323 Thu.

08:00 – 09:45

HB4

MDV

Agents and logic.
(AIMA, 2, 7.1-7.5.2, 8.1-8.3)

20230324 Fri.

13:15 - 15:00 

HB3

MDV

Probabilistic reasoning. 
(AIMA, 12.1-12.5, 13.1-13.3)

Hand-out of Assignment 1

20230327 Mon.

08:00 – 09:45

HB4

MDV

Clustering, classification, and decision-making, Part 1  
(AIMA, 15-15.3, 17.2, 19-19.2, 12.6, 21.2.2)

20230330 Thu.

08:00 – 09:45

HB4

DV

Exercise class

20230331 Fri.

13:15 - 15:00

HB3

MDV

Clustering, classification, and decision-making, Part 2  
(AIMA, (parts of) Chapter 19)

Break

 

 

 

 

20230413 Thu.

08:00 – 09:45

HB4

MDV

Stochastic optimization methods  
(AIMA, Chapters 3-4) 
Hand-out of Assignment 2. Hand-in of Assignment 1

20230414 Fri.

13:15 - 15:00

HA1

MDV

Robotics - perception and action  
(AIMA Chapter 26)

20230417 Mon.

08:00 – 09:45

HA4

MDV

Natural Language Processing and Conversational AI
(AIMA Chapter 24)

20230420 Thu.

08:00 – 09:45

HB4

DV

Exercise class

20230421 Fri.

13:15 - 15:00

HB4

MDV

Ethics in artificial intelligence
(AIMA Chapter 28), 

20230424 Mon.

08:00 – 09:45

HA4

BM

Introduction to machine learning with neural networks
Neural networks - Perceptrons (MLNN, Chapters 1 & 5, and Sections 8.1 & 8.2) 

20230427 Thu.

08:00 – 09:45

HB4

BM

Neural networks - Perceptrons (MLNN, Sections 5.1, 5.2, 5.3,  5.5)

20230428 Fri.

13:15 - 15:00

HB4

BM

Neural networks - stochastic gradient descent (MLNN, Sections 6.1 and 6.2 ) 
Hand-out of Assignment 3. Hand-in of Assignment 2

20230501 Mon.

Holiday 

 

 

(No lecture)

20230504 Thu.

08:00 – 09:45

HB4

BM

Neural networks
(MLNN, summary of Sections 6.3, 6.4, 6.5, 7.2, 7.3, 7.5, 7.6.1) 

 

20230505 Fri.

13:15 - 15:00

HB4

BM

Exercise class (neural networks)
Section 8.3 in MLNN and the material I went through in my earlier lectures.

20230508 Mon.

08:00 – 09:45

HB4

BM

Recurrent networks  (MLNN, Section 9.2)

20230510 Wed.

13.15-15.00

HA3

BM

Outlook  (MLNN, Chapter 10)

20230511 Thu.

08:00 – 09:45

HB4

MG

Introduction to Reinforcement learning. (MLNN Chapter 11 and/or RLAI, chapters specified under literature.)

Hand-out of Assignment 4 

20230512 Fri.

13:15 - 15:00

HA1

MG

Reinforcement learning: Summary of basic RL and intro to deep RL, Hand-in of Assignment 3

20230515 Mon.

08:00 – 09:45

HB4

BS/MG

Q&A on Assignment 4.  (Reinforcement learning)

Break

 

 

 

 

202305025 Thu.

08:00 – 09:45

HB4

MW

Course summary, Hand-in of Assignment 4

Course literature

[AIMA] Russell, S.J., Norvig, P. Artificial intelligence: A modern approach, 4th Edition (Selected chapters; see the schedule above). Note: previous editions may be used by students (see the comparison table).

[MLNN] Mehlig, Bernhard, Machine learning with neural networks. An introduction for scientists and engineers, (2021). Errata.
Chapter 1( introduction),
Chapter 5 (perceptrons),
Chapter 6 (stochastic gradient descent),
Chapter 7 (deep learning),
Chapter 8 (convolutional networks),
Chapter 11 (reinforcement learning).

[RLAI] Sutton, Richard S. & Barto, Andrew G.,  Reinforcement Learning: An Introduction (2nd ed.)
Read at least Chapter 1 (Introduction), Chapter 3 (Finite Markov Decision Processes), and Chapter 6 (Temporal-Difference Learning) up to and including 6.5. Chapter 16 (Applications and Case Studies) is also recommended for discussions on some of the early and recent high-profile application.  

For some lectures, additional material will be provided (free of charge) and will be uploaded on the course web page (under the module "Additional literature")

Slides of the lectures (see Modules).

Course design

The course consists of a sequence of lectures, usually two per week (but note that there are some exceptions; see the schedule above) as well as (usually) one exercise session per week.

The examination will be based on assignments; see below.

Changes made since the last occasion

No significant changes.

Learning objectives and syllabus

Learning objectives:

  • Describe, implement, and apply logic and probabilistic reasoning.
  • Describe, implement, and use various methods for classification, machine inference, clustering, planning, and decision-making
  • Describe, implement, and use basic conversational agents (human-machine dialogue)
  • Describe, implement, and use neural networks and deep learning
  • Describe, implement, and use reinforcement learning
  • Describe, implement, and use stochastic optimization algorithms
  • Analyse and critically discuss ethical aspects of AI and its applications
  • Discuss and analyze various applications of AI

Examination form

The examination will consist of four home problems, which the students should solve individually. There will be no final exam. The maximum number of points for the assignments will be as follows:

  • Assignment 1: 15p
  • Assignment 2: 35p
  • Assignment 3: 30p
  • Assignment 4: 20p

The hand-out and hand-in dates can be found in the schedule above. Penalties for delays and deductions in case of incomplete or erroneous solutions will be given separately in the text of each assignment.

Grades will be set as follows:

  • Grade 5: 80p -
  • Grade 4: 60-79p
  • Grade 3: 40-59p

Note that a minimum of 40p is required for a passing grade.

Course summary:

Date Details Due