course overview

This seminar-style course studies the topic of artificial intelligence. Presentations are mainly held by the students themselves. Goal of the course is to learn studying, processing and presenting scientific material, and to learn about artificial intelligence. The seminar consists of lectures, homework assignments, student presentations, a final project, and writing a paper. It covers various sexy topics from the field of artificial intelligence, to the level that should enable students to discuss AI comfortably with other scientists. The topics include the question of whether machines can think, evolutionary computation, neural networks, computing with DNA, computers and emotions, and more.

The selected topics were chosen to be practically applicable for future Media Technology projects, or to make students think about future directions. However, the course is open to students from other programmes and institutes also. It is not a complete overview of AI topics, and some topics are not strictly AI but somehow related. They were included because they are interesting and students should know something about them.

details

Lecturer:	Maarten Lamers, of the Media Technology MSc program at Leiden University
Teaching assistant:	Tijl Kindt is present during lectures. For help outside the lectures, make an appointment with the assistant.
Lecture room:	room 413 of the Snellius building
Schedule:	see the Media Technology MSc program calendar; also, see the detailed course schedule below
Language:	English
Level / Credits:	500 (scientifically oriented master course), 5 ECTS
Requirements:	compulsory attendance a good grasp of verbal and written English (required) active participation in class (required) some experience or affinity with computer programming (strongly recommended)
Grading:	35% homework tests (during class) 35% presentation 25% project and paper 5% participation in discussions + attendance (determined by lecturer) final result is rounded to nearest value accepted by Leiden University's grades-registration system
Enrollment:	students from outside the Media Technology program can do the course, but must send an e-mail beforehand to mediatechnology@leiden.edu requesting admittance; there is a class size restriction of 30 students
Communication:	check the Media Technology Forum regularly! Grades and performance feedback are published behind closed doors.
Study materials:	no book, only web-available materials. Note that many articles can be downloaded from the university's network only (not from home) due to copyright restrictions.
No-laptop policy:	during presentations by other students it is not allowed to have your laptop open, spend time on your iPhone, etcetera.

related courses, events and LIACS people

• Course Artificial Intelligence by Walter Kosters. It is (rather annoyingly!) offered in Dutch only
• Seminar Affective Computing by Joost Broekens at TU Delft
• Course Evolutionary Algorithms by Thomas Bäck (with lots of math)
• Course Neural Networks by Joost Kok is a good introduction to the field
• Course Data Mining by Joost Kok
• Workshop Artificial Creatures by Maarten Lamers and Peter van der Putten
• overview of all LIACS Computer Science BSc courses, Computer Science MSc courses, and ICT in Business MSc courses.

• Walter Kosters has much knowledge of AI in general
• Thomas Bäck is a professor specialized in natural computing
• Joost Kok is a professor with much AI knowledge, in particular neural networks and data mining
• Peter van der Putten is an AI and data mining specialist with much knowledge of collaborative filtering
• Maarten Lamers knows much about neural networks and Rodney Brooks
• Jetty Kleijn is specialized in the life of Alan Turing
• Hendrik Jan Hoogeboom knows much about DNA computing
• Joost Rekveld (Royal Academy of Art / Media Technology program) has an active interest in autonomous robots and artificial life
• Joost Broekens (former LIACS) is an expert on affective computing, reinforcement learning and artificial life
• Joris Slob is a Media Technology alumnus and currently a PhD student at LIACS. He has much general knowledge of AI, and semantic networks and logic programming in particular.
• and others...

homework

Before each class, students must read material about the discussed topic and answer some basic test questions at the start of class. The answers are graded and the average value of all homework results makes up a student's total homework grade. If a student does not attend the lecture, or is late for the homework test, a 0 is given (no exceptions).

A folder containing photocopies of all homework reading material is available in the Media Technology coordinator's office (Snellius building, room 106). Students can borrow this folder to make photocopies of the papers only if they return the folder immediately and don't mess up the pages. Also, the corrected homework assignments are in this folder for students to view.

presentations

There are two types of student presentations:

1. Primary Presentations, in which two students present the homework reading material and other material that they found themselves. Both students should speak for approximately equal parts of the total presentation. Each presentation should have two parts of 20 minutes each: the first part discusses the homework reading material, the second discusses applications (or examples) of the technique and why the technique is suited for such applications. For the second part, students should find their own material. Topics for primary presentations are assigned to pairs of students during lecture 1.
2. Secondary Presentations, in which single students present a published scientific article. Secondary presentations must take 20 minutes. They must start with clearly mentioning the title, authors, year of publication, and mention where it was published. Articles for secondary presentations are assigned to single students during lecture 1.

• Take your presentation very seriously and practice it! With the presentations you teach the rest of the class, which is a serious matter. Therefore I expect that you prepare very well and do your best.
• Presentations are graded on the choice of material, the displayed understanding of the material, and the structure of the presentation. Personal verbal skills are not graded, unless they make the presentation un-understandable. Primary presentations are graded per-duo, meaning that a single grade is shared by both students. If there is a substantial difference in the amount/quality of the work by both students, then they may be graded separately (Maarten decides). However, since both students are responsible for the total presentation, their separate grades will somehow reflect the average.
• Following each presentation there is room for questions and class discussion.
• Make sure you present clearly, so that I can judge your understanding of the material.
• If you want to use the video projector (beamer), make sure that the laptop and software run perfectly prior to your presentation! If you use a Mac computer, don't forget to bring a Mac-to-VGA-cable-thingy. Internet is available through cable only.

project and paper

Apply some form of "artificial intelligence" technique to achieve a task. Choose your own AI method for this, with the exception of Braitenberg-style vehicles and L-Systems. You can build a physical thing, such as a robot or an expressive installation, or a software thing. You can also do an interesting experiment involving artificial intelligence. Try to limit the amount of programming that you do, by using software from the web. There is a lot available.
Projects must be done in groups of two students (groups of three need permission). All students present their projects in class on the presentation date. The project presentations should take 7 minutes (maximally 10 minutes)!
Write a two-page paper explaining your project, using this Word template (also in RTF format). Papers can be submitted until one week after the presentation (see schedule below). Submitting your paper late without a really good reason will lead to a deduction of 0.5 upto 2 grade points. Submit by mailing the paper to lamers@liacs.nl

Alan Turing (1912-1954, UK; wikipedia) is the founder of computer science as we know it. His most important result was the "Turing Machine", with which he showed that all practical computing models are essentially equivalent (to put it shortly). He also played a large role within Artificial Intelligence, by developing the so-called "Turing Test".

[Turing 1950]	Alan M Turing (1950), Computing Machinery and Intelligence, Mind 49 Num 236, pp 433-460.
[Minsky 1982]	Marvin Minsky (1982), Why People Think Computers Can't, AI Magazine, Fall 1982, pp 3-15.
[Dennett 1990]	Daniel C Dennett (1990), Can Machines Think?, from The Age of Intelligent Machines, Ray Kurzweil, MIT Press. (original version)
[Searle 1990]	John R Searle (1990), Is the Brain's Mind a Computer Program?, Scientific American 262(1), pp 26-31.
[Churchland 1990]	Paul Churchland and Patricia Churchland (1990), Could a Machine Think?, Scientific American 262(1), pp 32-37.
[Dennett 1997]	Daniel C Dennett (1997), Consciousness in Human and Robot Minds, from Cognition, Computation, and Consciousness, by M Ito, Y Miyashita, and ET Rolls, Oxford University Press.
[Copeland 2000]	B Jack Copeland (2000), The Turing Test, Minds and Machines 10, pp 519-539.
[Rowlands 2003]	Mark Rowlands (2003), Terminator I and II, the mind-body problem, Chapter 3 (pp 57-85) of The Philosopher at the End of the Universe — Philosophy explained through science fiction films, Ebury Press (Note: this excellent book was retitled to Sci-Phi: Philosophy from Socrates to Schwarzenegger).
[Koch 2011]	Christof Koch and Giulio Tononi (2011), A Test for Consciousness, Scientific American June 2011, pp 44-47.

feedforward neural networks

Feedforward networks are a specific class of artificial neural networks. Basically, they can model relationships between pairs of data. For example, between the age, sex, background of a student and that student's grade in the Research Seminar. By applying a specific algorithm (e.g. backpropagation) they can adapt their internal parameters until they model relations in a dataset. This is commonly done by repeatedly presenting the network with example input/output pairs of data.

[Hinton 1992]	Geoffrey E Hinton (1992), How Neural Networks Learn from Experience, Scientific American September 1992, pp 104-109.
[Van Camp 1992]	Drew van Camp (1992), Neurons for Computers, Scientific American September 1992, pp 125-127.
[Dewdney: Neural Nets]	A.K. Dewdney (1993), Neural Networks That Learn, Chapter 36 (pp 241-249) of The New Turing Omnibus, Holt Publishers, NY.
[Kröse 1996]	Ben Kröse and Patrick van der Smagt (1996), An introduction to Neural Networks, unpublished book.
[Cawsey 1997]	Alison Cawsey (1997), Neural Networks, Sections 7.1, 7.2 and 7.6 of The Essence of Artificial Intelligence, Prentice Hall.
[Callan 2003]	Rob Callan (2003), Neural Networks I, Chapter 15 (pp 286-311) of Artificial Intelligence, Palgrave Macmillan.
[Russell 2003]	Stuart Russell and Peter Norvig (2003), Neural Networks, Section 20.5 (pp 736-748) of Artificial Intelligence, a Modern Approach (second edition), Prentice Hall Series in AI.

logic programming

[Dewdney: Logic Progr]	A.K. Dewdney (1993), Logic Programming, Chapter 64 (pp 420-426) of The New Turing Omnibus, Holt Publishers, NY.
[Lenat 1995]	Douglas B Lenat (1995), Artificial Intelligence, Scientific American, September 1995, pp 80-82.

semantic web

[Berners-Lee 2001]	Tim Berners-Lee, James Hendler And Ora Lassila (2001), The Semantic Web, Scientific American, May 2001, pp 35-43.
[Feigenbaum 2007]	Lee Feigenbaum, Ivan Herman, Tonya Hongsermeier, Eric Neumann, and Susie Stephens (2007), The Semantic Web in Action, Scientific American, December 2007, pp 90-97.

evolutionary computing

Evolutionary computing is the collective name for a range of problem-solving techniques (algorithms) based on principles of biological evolution, such as natural selection and genetic inheritance. Basically, their strategy is to create a collection of possible solutions for your problem (which may be very bad solutions) and to use the principles of evolution to evolve better solutions from this collection.

[Cawsey 1997]	Alison Cawsey (1997), Genetic Algorithms, Section 7.5 of The Essence of Artificial Intelligence, Prentice Hall.
[Eiben 2003]	AE Eiben and JE Smith (2003), Introduction to Evolutionary Computing, Springer. - Chapter 1, Introduction, pp 1-14 - Chapter 2, What is an Evolutionary Algorithm?, pp 15-35 - explanation of symbols used in Chapter 2, - Guszti Eiben worked at LIACS before becoming a professor in Amsterdam.
[De Jong 2006]	Kenneth A De Jong (2006), Introduction, Chapter 1 (pp 1-22) of Evolutionary Computing, a Unified Approach, MIT Press.

affective computing

Affective computing is not really artificial intelligence, but it is interesting nonetheless. Affective computing deals with devices that can process emotions. It is an interdisciplinary field, relating to computer science, psychology, and cognitive science.

[Picard 1996]	Rosalind W Picard (1996), Does HAL Cry Digital Tears? Emotion and Computers, Chapter 13 of HAL's Legacy: 2001's Computer as Dream and Reality, MIT Press.
[Picard 1997]	Rosalind W Picard (1997), Affective Computing, MIT Press.
[Picard 2000]	Rosalind W Picard (2000), Toward Computers That Recognize and Respond to User Emotion, IBM Systems Journal, Vol 39 Num 3-4, pp 705-719.
[Gibbs 2003]	W Wayt Gibbs (2003), Why Machines Should Fear, Scientific American, December 2003, pp 37-37A.
[Picard 2004]	Rosalind W Picard, et al. (2004), Affective Learning — a Manifesto, BT Technical Journal, Vol 22(4), pp 253-269.

biological computation and control

This is not really artificial intelligence. However, it is interesting to consider using true biological systems (not simulations) for computation. Can you mix computers with aminals, humans, or cells to solve problems? What is the currect state of cyborgs? Here are a few sources that I collected, but there are many more examples.

[Skinner 1960]	B.F. Skinner (1960), Pigeons in a Pelican, American Psychologist, Vol. 15, No. 1, pp 28-37.
[Nakagaki 2000]	Toshiyuki Nakagaki, Hiroyasu Yamada, Ágota Tóth (2000), Maze-Solving by an Amoeboid Organism, Nature 407, p 470.
	Video showing Nakagaki's experiment (interesting part starts at 3m20s).
[ScienceDaily 2004]	'Brain' In A Dish Acts As Autopilot, Living Computer, ScienceDaily.com, 22 October 2004.
[NewScientist 2006]	Robot Moved by a Slime Mould's Fears, NewScientist.com, 13 February 2006.
[Nature 2008]	Cellular Memory Hints at the Origins of Intelligence (2008), Nature 451, pp 385.
[ScienceDaily 2008]	Robot With A Biological Brain: New Research Provides Insights Into How The Brain Works, ScienceDaily.com, 14 August 2008.
[Adamatzky 2010]	Andrew Adamatzky and Jeff Jones (2010), Road Planning with Slime Mould: If Physarum built motorways it would route M6/M74 through Newcastle, in print.

artificial life and emergence

The field of Artificial Life attempts to simulate and study processes that we associate with living. It is a broad, and somewhat ill-defined field, but interesting nonetheless.

[Gardner 1970]	Martin Gardner (1970), The fantastic combinations of John Conway's new solitaire game "life", Scientific American 223, October 1970, pp 120-123.
[Wikipedia:Conway]	Wikipedia Entry for Conway's Game of Life.
[Braitenberg 1984]	Valentino Braitenberg (1984), Vehicles: Experiments in Synthetic Psychology, MIT Press, pp 1-19.
[Dewdney: Cellular]	A.K. Dewdney (1993), Cellular Automata, Chapter 44 (pp 295-300) of The New Turing Omnibus, Holt Publishers, NY.
[Steels 1994]	Luc Steels (1994), The Artificial Life Roots of Artificial Intelligence, Artificial Life Journal, Vol 1 Num 1-2, pp 75-110.
[Sipper 1995]	Moshe Sipper (1995), An Introduction to Artificial Life, Explorations in Artificial Life (special issue of AI Expert), pp 4-8.
[Bedau 2000]	Mark A Bedau, John S McCaskill, Norman H Packard, Steen Rasmussen, Chris Adami, David G Green, Takashi Ikegami, Kunihiko Kaneko, and Thomas S Ray (2000), Open Problems in Artificial Life, Artificial Life, Vol 6 Num 4, pp 363-376.
[Brooks 2001]	Rodney Brooks (2001), The Relationship Between Matter and Life, Nature 409, pp 409-411.
[Packard 2003]	Norman H Packard and Mark A Bedau (2003), Artificial Life, Encyclopedia of Cognitive Science, Vol 1, Macmillan Publ., pp 209-215.
[Velleman Microbug]	The Velleman company created a cheap (~10 EURO) Braitenberg vehicle kit, called the MK127 Microbug. Some electronics supplies stores sell it, or you can order it at many online electronics stores. (I have a bunch, so let me know if you want to borrow them.)

social robotics

[Fong 2003]	Terrence Fong, Illah Nourbakhsh, Kerstin Dautenhahn (2003), A Survey of Socially Interactive Robots, Robotics and Autonomous Systems 42, pp 143–166.
[Dautenhahn 2007]	Kerstin Dautenhahn (2007), Socially Intelligent Robots: Dimensions of Human–Robot Interaction, Philosophical Transactions of the Royal Society B vol. 362, pp 679–704.
[Levy 2008]	Not Tonight, Dear, I Have to Reboot, Scientific American, March 2008, pp 94-97.