Course syllabus
Course memo
MMS130 Introduction to Artificial Intelligence, SP4, 2021 (7.5 hp)
The course is offered jointly by the department of Mechanics and Maritime Sciences (M2) and the Physics department (F)
General information
This year, with the ongoing pandemic, the course will be given in a different way than usual. There will be no classroom lectures. Instead, each lecture will (normally) consist of a video with a recorded presentation of the lecture (uploaded a before the scheduled time of the lecture; see below), directly followed by an interactive session on Zoom, where the teacher will discuss the contents of the lecture with the students, and also answer any questions that the students might have. In addition, students are welcome to ask questions or give feedback at any time (see also Contact details below).
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 Zoom session associated with each lecture or at other times, and you may also ask questions via e-mail or telephone. You are always welcome at our offices, in principle. However, due to the pandemic, we mostly work from home, so 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:
Professor Mattias Wahde (MW), Tel: 772 3727, e-mail: mattias.wahde@chalmers.se
Lecturers:
Professor Mattias Wahde (MW), Tel: 772 3727, e-mail: mattias.wahde@chalmers.se
Professor Bernhard Mehlig (BM), e-mail: bernhard.mehlig@physics.gu.se
Senior Lecturer Mats Granath (MG): Tel: 0723087160, e-mail: mats.granath@physics.gu.se
Teaching assistants:
Victor Ebberstein (VE), e-mail: vicebb@chalmers.se
Anshuman Dubey (AD) e-mail: anshuman.dubey@physics.gu.se
Basudha Srivastava (BS), e-mail: basudha.srivastava@physics.gu.se
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. The "Publish time" refers to the time when the pre-recorded video (for the lecture in question) will be uploaded (on the Modules page), when applicable For each lecture there will also be a live Zoom session, starting at the nominal lecture time (see the corresponding column). The schedule can also be found at TimeEdit but note that the duration of the (Zoom) lectures is as shown below. Some Zoom sessions might be slightly longer (depending on the number of questions, for example), but they will never exceed the nominal duration (2 x 45 min.) in TimeEdit. Note: The course is given for the first time. Hence, there might be minor changes in the schedule below. If so, the changes will be announced well before the lecture(s) in question.
Description:
"Publish time" = the latest time at which the video lecture will be published (sometimes earlier)
"Content": Brief summary of the contents, with references to the course material; see above.
| Date | Teacher | Publish time | Zoom session | Content |
| 20210322 | MW | 16.00 (20210321) | 08.00-08.45 | Course introduction, general overview of course topics |
| 20210325 | MW | 16.00 (20210324) | 08.00-08.45 | Agents and logic. AIMA, Chapters 2, 7-8 (2.1-2.5, 7.1-7.5.2, 8.1-8.3, 8.5) |
| 20210326 | MW | 08.00 | 13.15-14.00 | Probabilistic reasoning. AIMA, Chapters 13-14 (13.1-13.5,13.7,14.1-14.2, 14.4, 14.8) |
| 20210329 | VE | --- | 08.00-09.45 | Exercise class (related to the lecture on 20210325) Problems demonstrated by the TA: 2.1, 2.11 (a-d), 7.2, 7.4 (c-e), 7.17 (a-c), 8.9 (a-d), 8.19, 8.20 (a-b) Recommended problems (for students to solve): 7.1, 7.4 (a-b,f-k), 7.7 (a-c), 8.6, 8.9 (e-g), 8.26 (a-f) |
| 20210412 | MW | 16.00 (20210411) | 08.00-08.45 | Clustering, classification, and decision-making, Part 1 (AIMA, (parts of) Chapters 16-18, as well as separate lecture notes) Hand-out of Assignment 1 |
| 20210415 | MW | 16.00 (20210414) | 08.00-08.45 | Clustering, classification, and decision-making, Part 2 (AIMA, (parts of) Chapter 18 as well as separate lecture notes) |
| 20210416 | VE | --- | 13.15-15.00 |
Exercise class (Related to the lectures on 20210326, 20210412) |
| 20210419 | MW |
16.00 (20210418) |
08.00-08.45 | Stochastic optimization methods (AIMA, Chapters 3-4, as well as separate lecture notes) Hand-in of Assignment 1, Hand-out of Assignment 2 |
| 20210422 | VE | --- | 08.00-09.45 |
Exercise class (Related to the lectures on 20210415, 20210419) Recommended problem (for students to solve): 18.24b (decision trees) |
| 20210423 | BM | - |
13.15-15.00 |
Introduction to machine learning with neural networks |
| 20210426 | BM | 08.00-09.45 |
Neural networks - Perceptrons |
|
| 20210426 | VE | --- | 13.15-15.00 |
Extra Q&A session on the topics of GAs and PSOs (primarily). |
| 20210429 | BM | - | 08.00-09.45 |
Neural networks - stochastic gradient descent |
| 20210503 | BM | - |
08.00-09.45 |
Neural networks - Deep learning |
| 20210506 | AD | --- |
08.00-08.45 | Exercise class (neural networks) Zoom link Hand-in of Assignment 2 |
| 20210507 | BM | - | 13.15-15.00 |
Neural networks - convolutional networks |
| 20210510 | MG | Live lecture (will be recorded) | 08.00-09.45 |
Introduction to Reinforcement learning. Recommended reading: see course literature [3]. Zoom link: https://chalmers.zoom.us/j/65371311908 Password: 621776 |
| 20210514 | AD | --- | 09.00-10.00 |
Extra Q&A session on the topics of deep learning (for Assignment 3, primarily) Zoom link |
| 20210517 | MG | Live lecture (will be recorded) | 08.00-08.45 |
Reinforcement learning, Part 2. Summary of basic RL and intro to deep RL Recommended reading: see course literature [3]. Zoom link: https://chalmers.zoom.us/j/64106562577 Password: 483508 Hand-in of Assignment 3, Hand-out of Assignment 4 |
| 20210520 |
BS and MG |
--- |
08.00-09.15 Note, finishes at 9.15. |
Q&A Session on Assignment 4. Bring your questions. We can use breakout rooms for individual discussions. Zoom link: https://chalmers.zoom.us/j/63234039805 Password: 870002 |
| 20210521 | MW | 08.00 | 13.15-14.00 | Robotics - perception and action (AIMA Chapters 24-25) |
| 20210524 | MW | 20210523 (16.00) | 08.00-08.45 | Conversational agents (separate lecture notes) |
| 20210524 | BS and MG | 10.00-11.45 |
Extra Q&A Session on Assignment 4 Zoom: https://chalmers.zoom.us/j/66733442349 |
|
| 20210527 | MW | 20210526 (16.00) | 08.00-08.45 | Ethics in artificial intelligence (separate lecture notes), Hand-in of Assignment 4 |
| 20210528 | MW | Live lecture (not recorded) | 13.15-14.00 | Course summary |
Zoom links (for the interactive sessions)
Mattias Wahde:
https://chalmers.zoom.us/j/2039626788
passcode: 2020FFR105 (unchanged from the previous course)
Bernhard Mehlig: different zoom links for different lectures, see above.
Mats Granath: Posted in the schedule, above.
Victor Eberstein:
https://chalmers.zoom.us/j/8487968589
passcode: MMS130
Anshuman Dubey:
passcode: MMS130
Course literature
[1] Russell, S.J., Norvig, P. Artificial intelligence: A modern approach, 3rd (note!) Edition (AIMA) (Selected chapters; see the schedule above).
[2] Mehlig, Bernhard, Machine learning with neural networks. An introduction for scientists and engineers, (2021).
Chapter 5 (perceptrons), Chapter 6 (stochastic gradient descent), Chapter 7 )(deep learning), Chapter 8 (convolutional networks), Chapter 11 (reinforcement learning)
[3] 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")
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.
Learning objectives and syllabus
Learning objectives:
After completing the course, the students should be able to
- 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
Link to the syllabus on Studieportalen.
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 |
|---|---|---|