======T-720-ATAI, ADVANCED TOPICS IN ARTIFICIAL INTELLIGENCE, Fall 2018====== ====See Canvas For Up-To-Date Information, Notifications, Links to Lecture Notes==== **Instructor: Kristinn R. Thórisson** \\ **Teaching Assistants: TBD** \\ **8 ECTS Units, full Master's-level course** \\ **Readings:** [[:public:t-720-atai:ATAI-18:Readings|Readings in SC-T-720-ATAI-18]] \\ **Lecture Notes:** [[:public:t-720-atai:ATAI-18:Lecture_Notes|Lecture Notes in CS-T-720-ATAI-18]] \\ **Days: Mondays** | **Time: 14:00-14:45 / 14:55-15:40** | **Classroom: M108** \\ **Class Schedule:** See Canvas \\ Discussions: [[https://piazza.com/class/jl2e5nca23b7gz|SC-T-720-ATAI-18 on Piazza]] \\ \\ ====Course Description==== The course focuses on the phenomenon of intelligence and how to create a truly intelligent machine. In the past 10-15 years attempts to answer this question has been have been made under the rubric of //artificial general intelligence (AGI)//, //developmental robotics// and //cognitive robotics//. Looking further into the future than allowed by mere linear extrapolations of popular technologies being applied in various industries today, the course centers on the issues of intelligence architecture, system autonomy, realtime attention, anytime planning, model-based knowledge representation, and what could be considered holistic integration issues. Ideas from systems theory, constructivist AI, control theory and cybernetics provide a conceptual foundation. The course takes inspiration from the questions asked by the founders of the field of A.I., e.g. Turing, McCarthy, Minsky and others, -- //What is intelligence?// and //How can we implement intelligence in a machine?// -- as well as the ideas of cyberneticians and early pioneers of systems science. Historical background and relevant topics from constructionist AI ("good old-fashioned AI") provide a contrasting backdrop for our treatment of how to build more autonomous and self-contained intelligent systems than possible with today's methods. Relevance of AGI to autonomous robotics and systems operating in the physical world will be addressed. ===Prerequisites & Requirements=== * Programming experience necessary (LISP, Prolog, Haskel or related is a plus) * A prior introductory class in one or more of the following is recommended: Artificial intelligence, simulation techniques, cognitive science. * Dedication. * Patience, resilience, and focus to read at 2-3 papers per week. === Goals === After taking the course, diligently attendeding the classes and doing the assignments, thoroughly reading, and actively participating in discussions, students should be able to: * Identify key challenging research questions related to advanced machine learning and (AML) artificial general intelligence (AGI) * List methodological difficulties and proposed solutions to building AML/AGI systems * Explain key components of some AML/AGI architectures, and how these relate to the creation of truly intelligent machines of the future * Students should have a good idea of: * The limitations of current AI methodologies * How AGI differs from "narrow AI" * Some AML/AGI projects in progress * What the main requirements are for building complete minds * What methodologies are currently available and applicable for building complete minds * How software architecture plays a central role in AI, robotics, and AGI * How to apply presently-known techniques and methodologies for building complex AI systems * Emergence, self-organization, and synergism * Students will have had hands-on experience with: * Selected machine learning methods, notably reinforcement learning * One programming environment targeting AGI \\ ====Assignments==== //Note: This assignment outline is indicative only; until Sept. 30st some details of these assignments, and their percentage of total grade, may change. Please take note of announcements on Canvas. // * Students should hand in their assignments (using Canvas) on time; if there will be any unnecessary delay in handing in the assignment then students must assume the possibility of a lowered grade. === Small Projects === These will be given in the first half of the course. * Individual programming assignments will be handed out in the first 8 weeks. * Each assignment counts 5% of the final grade. An extra 1% bonus point (over and above 100%) will be given for quality hand-ins (quality is judged by the depth of the insights expressed, meticulousness, thoroughness and overall quality and coherence). * The code for TEAL can be found here: [[https://github.com/ThrosturX/rl-mouse|TEAL on GitHub]] * Instructions for each exercise will be provided at the end of the class they are assigned in. * [[:public:t-720-atai:ATAI-18:Braitenberg Assignment|Braitenberg Assignment]] * **Grading: 15%** of final grade. === Class Discussions === This will be pursued in the second half of the course. * Regular Discussions of reading material will be held for 30-40 minutes in class. * For discussions we will use the forum on [[https://piazza.com/ru.is/spring2018/t720atai2018/home|Piazza.com]]. * After most Tuesday classes in the second half of the course the instructor will post a link on the online forum to a paper or article on an interesting aspect of AI (more likely than not related to the last 2 week's lecture topics). You need to read this paper or article and by midnight on the following Thursday post, under the same forum thread, 2 questions you have about the contents of the material. * Your posting must arrive by 23:59 on Thursday night (unless an exception has been explicitly mentioned) to count towards your **paper discussion grade**. * The questions can point out concepts that you have difficulty understanding, but preferably they should be questions that //provoke discussion// from the material. * In the discussion section of the following Tuesday class, chosen questions from those submitted will be discussed by the group as a whole and you are expected to participate. * Participation in class discussions is an important part of the course, and mandatory. * **Grading: 20%** of final grade. * Each topic counts equally towards the grade * Attendance in 2 in-class discussions may be omitted with no effect on grade * In-person attendance at 2 discussion classes may be omitted with no effect on grade === Final Project === * As a final software exercise students will pair up in teams of 2 students per team. The final form will be decided before Sept. 20. To give you already an idea of its form, this project will be of your own design, using: * the AGI-aspiring system NARS [[http://code.google.com/p/open-nars/|NARS environment]] (see [[http://code.google.com/p/open-nars/source/browse/trunk/nars-dist/Examples/|examples]]) * **Grading of software assignments: 15%** of final grade. * [[:public:t-720-atai:ATAI-18:final project|Final Project]] ===Final Exam=== * Final Exam will **count 45%** of final grade. //Note: percentage of final grade may change.// * Subject matter / focus: Any of the material and topics covered in readings, assignments, discussions, and in class. * A grade of 6 or higher on the final exam is required to pass the course. * Hand-in of the assignments is not a requirement to get permission to take the final exam. * Expect to draw architectural diagrams, write pseudo-code, and write (short) essays in the final exam. * Closed-book: No helping material is allowed. * [[:public:t-720-atai:ATAI-18:final_exam_examples|Example Final Exam Questions]] \\ \\ --------------------------------------- --------------------------------------- //EOF//