|
“The question of whether a computer can think is no more interesting than the question of whether a submarine can swim.” — Edsger Dijkstra (very influential Dutch computer scientist; wikipedia) |
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 7 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 others.
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.
| Lecturer: | Maarten Lamers, of the Media Technology MSc program at Leiden University |
| Teaching assistant: | Joris Slob is present during lectures. For help outside the lectures, make an appointment with Joris. |
| Lecture room: | room 413 of the Snellius building |
| Schedule: | included in 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: |
|
| Grading: |
|
| Enrollment: | students in the Media Technology MSc program can register during Lecture 1; students from other programs should send an e-mail beforehand to the Media Technology programme coordinator at mediatechnology@leiden.edu requesting admittance (see requirements); there is a class size restriction of 30 students |
| Communication: | static information is posted on this webpage. Announcements during the course period will be posted on the Media Technology Forum, students must check this forum regularly! |
| 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. |
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.
There are two types of student presentations:
Simply apply some form of "artificial intelligence" technique to achieve a task. Choose your own AI method for this. 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).
Write a two-page paper explaining your project. You can use this Word template (also in RTF format) for writing your paper. All students present their projects in class on the presentation date. The project presentations may take maximally 10 minutes!
Papers can be submitted one week later (see schedule below).
| lecture date | presentations | homework reading | |
| 1 | Thursday January 14, 2010 | context and history of AI (Maarten Lamers) | none |
| 2 | Thursday January 21, 2010 | Can machines think? (Nisaar, Klaas-Jan) Chinese room argument (Veneta) [Dewdney: Game Trees] (Joost) |
[Dennett 1990] [Searle 1990] |
| 3 | Thursday January 28, 2010 | feedforward neural networks (Atze, Roland) logic programming (Joris Slob) |
[Hinton 1992] [Cawsey 1997] |
| 4 | Thursday February 4, 2010 | evolutionary computing (Peter, Marijke) affective computing (Manuel, Luis) |
Chapter 2 of [Eiben 2003] [Picard 2004] [Gibbs 2003] |
| 5 | Thursday February 11, 2010 | biological computation and control (Machteld, Marilena) artificial life (Auke, Niels) |
[Nakagaki 2000] [ScienceDaily 2004] [Nature 2008] [Braitenberg 1984, p 1-19] [Dewdney: Cellular] [Brooks 2001] |
| - | Thursday February 18, 2010 | class was cancelled | |
| 6 | Thursday March 4, 2010 10h30 - 15h30 (incl. lunch-break) |
|
[Dewdney: Analog] [Bonabeau 2008] |
| 7 | Thursday March 11, 2010 10h30 - 15h30 (incl. lunch-break) |
|
[Brooks 1991a] [Adleman 1998] |
| 8 | Thursday March 25, 2010 11h00 - 16h00 |
project presentations by all students Location: room 011, Gravensteen building, Pieterskerkhof 6 |
none |
| - | Thursday April 8, 2010 | Submission deadline for project paper (no lecture). Mail it to "lamers" and "jslob", both @liacs.nl. | |
Below is a literature list for this course, sorted per topic. Some items are homework reading material, others are recommended reading. Be aware that many links only work from within Leiden University's computer network! This implies that you may not be able to access them from home. Several articles were placed behind a username/password combination, which you can get from the lecturer.
The course organization is discussed and an introduction to the field of Artificial Intelligence is given, by way of its relations to other fields and its history. All presentations on this day are by Maarten.
| [Russell 2003] | Stuart Russell and Peter Norvig (2003), Introduction, Chapter 1 (pp 1-31) of Artificial Intelligence, a Modern Approach (second edition), Prentice Hall Series in AI. |
| [Callan 2003] | Rob Callan (2003), Introduction, Chapter 1 (pp 2-16) of Artificial Intelligence, Palgrave Macmillan. |
| [McCarthy 2006] | Getting Machines to Think Like Us (3 July 2006), CNET News interview with pioneer John McCarthy about 50 years of AI research. |
| [Luger 2009] | George F Luger (2009), AI: Early History and Applications, Chapter 1 (pp 3-33) of Artificial Intelligence: Structures and Strategies for Complex Problem Solving, Addison-Wesley. |
| [lecture slides] | Maarten Lamers, slides of introduction lecture (in PDF format) 2 slides-per-page or 6 slides-per-page. |
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. |
| [Dennett 1990] | Daniel C Dennett (1990), Can Machines Think?, from The Age of Intelligent Machines, Ray Kurzweil, MIT Press, pp 48-61. (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. |
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, Section 7.6 (pp 156-163) 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. |
| [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. |
| [Berners-Lee 2001] | Tim Berners-Lee, James Hendler And Ora Lassila (2001), The Semantic Web, Scientific American, May 2001, pp 35-43. |
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.
| [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 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. |
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.
| [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. |
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.) |
| [Reynolds 1987] | Craig W Reynolds (1987), Flocks, Herds, and Schools: A Distributed Behavioral Model, ACM SIGGRAPH Computer Graphics 21(4), July 1987, pp 25-34. |
| [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. |
| [Brooks 1990a] | Rodney Brooks (1990), Elephants Don't Play Chess, Robotics and Autonomous Systems 6, pp 3-15. |
| [Brooks 1991a] | Rodney Brooks (1991), Intelligence Without Representation, Artificial Intelligence 47, pp 139-159. |
| [DeMers 1993] | David DeMers and Garrison Cottrell (1993), Non-Linear Dimensionality Reduction, Advances in Neural Information Processing Systems 5, pp 580-587. |
| [Dewdney: Game Trees] | A.K. Dewdney (1993), Game Trees, Chapter 6 (pp 38-41) of The New Turing Omnibus, Holt Publishers, NY. |
| [Dewdney: Analog] | A.K. Dewdney (1993), Analog Computation, Chapter 33 (pp 223-230) of The New Turing Omnibus, Holt Publishers, NY. |
| [Maes 1994] | Pattie Maes (1994), Agents That Reduce Work and Information Overload, Communications of the ACM 37(7), pp 30-40. |
| [Liebowitz 1995] | Jay Liebowitz (1995), Expert systems: a short introduction, Engineering Fracture Mechanics Vol 50, Num 5/6, pp 601-607. |
| [Adleman 1998] | Leonard M Adleman (1998), Computing with DNA, Scientific American August 1998, pp 54-61. |
| [Gershenfeld 1998] | Neil Gershenfeld and Isaac L Chuang (1998), Quantum Computing with Molecules, Scientific American June 1998, pp 66-71. |
| [Boden 1998] | Margaret A Boden (1998), Creativity and Artificial Intelligence, Artificial Intelligence Vol 103 Num 1, pp 347-356. |
| [Sutton 1998] | Richard S Sutton and Andrew G Barto (1998), Introduction, Chapter 1 of Reinforcement Learning: An Introduction , MIT Press. |
| [West 2000] | Jacob West (2000), The Quantum Computer: An Introduction, online resource. |
| [Webb 2002] | Barbara Webb (2002), Robots in Invertebrate Neuroscience, Nature 407, pp 359-363. |
| [Linden 2003] | Greg Linden, Brent Smith, and Jeremy York (2003), Amazon.com Recommendations: Item-to-Item Collaborative Filtering, IEEE Internet Computing Vol 7(1), pp 76-80. |
| [McCormack 2005] | Jon McCormack (2005), Open Problems in Evolutionary Music and Art, Proceedings 3rd European Workshop on Evolutionary Music and Art (EvoMUSART), LNCS Vol 3449, pp 428-436. |
| [Shapiro 2006] | Ehud Shapiro and Yaakov Benenson (2006), Bringing DNA Computers to Life, Scientific American May 2006, pp 44-51. |
| [Bonabeau 2008] | Eric Bonabeau and Guy Theraulaz (2008), Swarm Smarts, Scientific American Special Editions 18(1), Your Future With Robots, pp 42-49. |
HW1 ... HW6 are the individual homework grades.
HW-MIN is the lowest of the individual homework grades.
HW-AVG is the the average homework grade, excluding the lowest individual grade.
PRES is the presentation grade.
PROJ is the project grade.
PARTIC is 1.0 point on the final grade, just for taking part in the course.
ROUND is the final grade, rounded according to the rules of our Graduate School.
STUD-ID HW1 HW2 HW3 HW4 HW5 HW6 HW-MIN HW-GR PRES PROJ PARTIC ROUND 0967300 4 6 3 4 7,5 7,5 3 5,8 7,75 7,5 10 7,00 0938629 7 7 7 7,5 7 5,5 5,5 7,1 9 8,25 10 8,00 0886157 6,5 6 10 6,5 7 6 6 7,2 6,5 5,5 10 6,50 0949671 5 8 8 7 7,5 8 5 7,7 8 7,5 10 8,00 0973580 8 8 7 7,5 6 8 6 7,7 9 8,25 10 8,50 0963712 6 6 7 7 6,5 7 6 6,7 6,5 8,25 10 7,00 0963445 6 8 6 7 8 7,5 6 7,3 8 8 10 8,00 0967998 4 10 8 8 7 9 4 8,4 8 8,25 10 8,50 0976164 6 6 0 6,5 6 1 0 5,1 7,5 8,25 10 7,00 E.A.D 7 7 7 7,5 7 0 0 7,1 7,5 7,5 10 7,50 0936774 6 8 0 7 5,5 4,5 0 6,2 7 5 10 6,50 0948209 5 10 5 6,5 7 9 5 7,5 8,5 6,5 10 7,50 0951692 5 3 8 6,5 7,5 6 3 6,6 8 5,50 10 7,00 0979414 8 8 8 8,5 9 7,5 7,5 8,3 7 9 10 8,00 0968005 8 10 8 9,5 8,5 10 8 9,2 8 8 10 8,50 0968013 8 9 10 8 7,5 9 7,5 8,8 9 8,25 10 9,00 0992305 6 8 9 6 5,5 7 5,5 7,2 8 5 10 7,00 0978094 7 7 7 6 7,5 8 6 7,3 7 7,25 10 7,50 0633054 10 7 7 5,5 6 7,5 5,5 7,5 7 5 10 7,00 0937093 7 9 5 7 8 5 5 7,2 7,5 5 10 7,00 0949728 6 9 9 7 7,5 6 6 7,7 8,5 6,5 10 8,00 0949604 9 10 10 8,5 8,5 10 8,5 9,5 9,5 7,5 10 9,00 0239356 6 8 0 6,5 0 8,5 0 5,8 6,5 8 10 7,00 0978124 3 7 8 6 8 7 3 7,2 7 7,25 10 7,50
Can Machines Think?
(s0979414, s0633054)
Grade: 7
Good that you added philosophical information to the content of Dennett's paper. Interesting how you note that Dennett's position appears to change in the (long) article. The presentation structure appeared quite "rommelig" (this also holds for the part about Turing himself), and lines were difficult to follow. It would have been better to be more concise and elaborate less. The formal logic example was somewhat unclear. Good that you looked back on the topic of combinatorial explosion, and made the bridge to Searle.
Searle's Chinese Room Argument.
(s0938629)
Grade: 9
Beautiful mix between content of the paper and additional information that you found (e.g. Functionalism vs Behaviourism). Clear understanding of the topic; this was clear from your discussion involving syntax vs semantics. Good that you chose your own line, and not strictly the line of the paper. Overall, your presentation gave added value to reading the paper.
Game Trees
(s0966533)
Grade: 6
You understood the material well. Maybe too well... The scope of your presentation was too ambitious. Teaching requires going over the steps carefully, so that everyone can follow: some steps you made were giant leaps to others. The text was not required reading for everyone, and therefore new to most of the class. It was good that you included an interactive demo of the algorithm, although it required some further explanation. Good that you mentioned other application fields of game trees.
Neural Networks
(s0239356, s0963712)
Grade: 6,5
Good that you included a history of neural networks yourself. The biological intro was fine, but went into more detail than required to understand artificial neurons. The explanation of feedforward neural networks could have been better; perhaps you understand it well, but the presentation style was very "rommelig" and therefore unclear. I hoped for better examples: they were not about NN's (the robot) or it was not clear what the role of NN's was (e.g. atmospheric interference correction). The closing analysis was OK.
Overall, I got the feeling that you could understand the topic, but that you didn't care to present it well. The presentation style was so nonchalant that you gave the impression that none of it was worth presenting or listening to.
Evolutionary Computing
(s0951692, s0967998)
Grade: 8
Well-structured presentation (biology -> EA's -> examples), with excellent tempo. The TSP example required some explanation; the step-by-step MasterMind example was very clear and well-poistioned within the presentation. The total presentation was short (30 minutes). The GAR example video was not a good choice: it did not make anything clear. Other examples of applications (in the remaining time) would have been better. It was a good decision not to follow the Eiben chapter too closely.
Affective Computing
(s0948209, s0949728)
Grade: 8,5
Clear presentation, from which it was evident that you understand the topic well. The presentation structure did not follow Picard's and Gibbs' papers, which was a good choice. I would liked to have seen emotion synthesis (not related to human interaction) more prominently, as I explained after the presentation. Nice balance between in-depth information and broad information. Also very clear presentation styles by both of you.
Biological Computing and Control
(s0937093, s0976164)
Grade: 7,5
Clear structure with good self-made categorization of sub-fields. You clearly made an effort. Interesting that you included "bacterial computing", which is a recent development and fits well in the theme, and that you extended all the way to Kevin Warwick. Good use of video's, although they occasionally required more explanation. Some material on slides (e.g. explanation of DNA computing) was too "massive" in the sense that it was hard for us to follow so much text. Your own understanding of some topics could have been better. Pros-and-cons list was a good idea, but cons focussed too much on DNA computing. Good that you reflected on ethics.
Artificial Life
(s0978124, s0978094)
Grade: 7
Clear structure (wet/hard/soft or weak/strong a-life) and nice that you included arts as a context. Also, the historical perspective through introduction of scientists was useful. Unfortunately, much of the presentation did not follow these structures. They could have been "deepened". The examples were often unclear -- this could have been prevented with better explaining. This is a risk when using video or live demo's. The game-of-life demo's had unclear purpose, although the explanation and showing of its rules was very good.
Swarm Smarts
(s0992305)
Grade: 8
Nice that you did not stick too close to the paper, because everyone had already read it. Nice that you attributed the definition to its author. Good that you mentioned different algorithms, for context, and did not go into them too much in the little time that was given. It appeared that much focus was on robot-based systems, and less on simulation, which in reality is the larger application field. Good that you mention the conference, since it is accessible.
Crowdsourcing
(s0968013, s0973580)
Grade: 9
Very good presentation. Your quick mention of "people researching crowdsourcing" gave historical context. Good theoretical framework. Excellent that you made your own subdivision of crowdsourcing research, which seems very logical. The M&M example slightly disrupted the attention from the group. Good presentation style: relaxed but focussed.
Lindenmayer Systems
E.A.D.
Grade: 7,5
Excellent start with the UK coast example. Also good that you continued into nature and growth-patterns. The leap to the abstract notion of L-Systems was somewhat large; the connection to natural growth systems seemed somewhat lost. Try to show how students in class can use/apply the technology. Good that you showed and played with the LMUSE system. You seem to understand the topic well.
Brooks
(s0967300)
Grade: 7,75
A very clear presentation about the ideas of Rodney Brooks. You seem to understand the topic well. Lthough Brooks was involved in the Kismet (robot head) experiments, I am not sure that they are examples of subsumption (layered) architectures. The presentation was complete, and you nicely did not go into details about the subsumption architecture. Avoid reading out text, but further good presentation style.
DNA Computing
(s0949604)
Grade: 9,5
An excellent presentation that covered DNA computing as a whole, not just the Adleman experiment. Very complete overview of the field since 1994 (Adleman). Your understanding of the different experiments is impressive. It was a lot of information for 25 minutes, but your decision to include it was good. Perhaps next year it should be a 45-minute topic. The speed at which you presented was high (perhaps because of time constraints). The slides were of excellent quality.
AI and Pop-culture
(s0968005, s0963445)
Grade: 8
A difficult topic because of its ill-definedness (both what AI is and what pop-culture is). It was good that you started with your own definition, and it was clear that you did your best to structure and elaborate on the topic. Occasionally it was hard to follow the two of you interacting before the class.
Flocking
(s0936774)
Grade: 7
Nice that you started with a video to explain the general/natural concept of flocking. The switch from natural to artificial (modelled) flocking was somewhat unclear, and the boids-model could be introduced more before going into the acting forces. Good that you included uses of such models.
Artificial Creativity
(s0949671)
Grade: 8
The paper by Boden is very formal and boring. You managed to abstract it into little chunks of information that were clear to understand and follow. The clear structure of the presentation helped this. You chose to stick closely to the paper; I would have liked to see some more outside information and personal opinion (you had it, but it only showed during the discussion). The speed of presentation was very good: not too fast, not too slow. Overall it was interesting and clear.