User Tools

Site Tools


public:t-720-atai:atai-16:main

T-720-ATAI, ADVANCED TOPICS IN ARTIFICIAL INTELLIGENCE, SPRING 2016

This Is The Main Page For The Course

Instructor: Kristinn R. Thórisson
Teaching Assistants: Jordi Bieger (Throstur Thorarensen)
8 ECTS Units, full Master's-level course
Days: Tuesdays & Fridays | Time: 12:20 - 13:50 | Classroom: M113
Class Schedule | Readings
W5 FEB | W6 FEB | W7 FEB | W8 MAR | W9 MAR | W10 MAR
T-720 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 linear advances on some of the most 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, 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 discussed.

Prerequisites

  • 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 attended the classes and doing the assignments, thorough reading, and participation in discussions, students should be able to:

  • Identify key challenging research questions related to advanced machine learning and (AML) artificial general intelligence (AGI)
  • List the 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


Readings

  • Readings and Study Material page - readings and material organized by topic.
  • To see readings in temporal order, see schedule below on this page.
  • Readings for the class will be published incrementally.


Assignments

Note: This assignment outline is indicative only; until February 31st some details of these assignments, and their percentage of total grade, may change.

  • Students should hand in their assignments (using MySchool) on time; if there will be any unnecessary delay in handing in the assignment then students must assume the potential of a resulting lower grade.

Programming Assignments

These will be assigned regularly 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: TEAL on GitHub
  • Instructions for each exercise will be provided at the end of the class they are assigned in.
  • 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 Friday classes.
  • For discussions we will use the forum on 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 by Thursday at midnight and post, under the same forum thread, 2 questions you have about the contents of the reading.
    • 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

Pair Programming Project

  • As a final programming exercise students will pair up in teams of 2 students per team. We will decide no later than Feb 19 whether this project will be:
    • A project of your own design using the TEAL platform.
    • A project of your own design using the AGI-aspiring system NARS NARS environment (see examples).
    • Some other kind of project and/or combination of things.
  • Grading of programming assignments: 10% of final grade. Note: percentage of final grade may change.

Short Essay

  • One short essay.
  • Document & Presentation: 10% of final grade.
  • Due: April 8 @ 10:00 am
  • Mandatory presentation of Short Essay: April 8 @ 12:20 - 14:00

Final Exam

  • Final Exam will count 45% of final grade (includes 2 bonus points, each counting 0,25 out of 10,0). Note: percentage of final grade may change.
    • Subject matter / material: Any and all material covered, in readings, assignments, discussions, and in class.
    • A grade of 4,75 or higher on the final exam is required to pass the course.
    • Handing in the assignments is not a requirement to get permission to take the final exam.
    • Assume to be able to draw architectural diagrams, write pseudo-code, and write (short) essays.
    • Closed-book: No helping material is allowed.





Class Schedule

W1 JAN

F-1 TUE 12.01.2016
Topics: Introduction to course structure, programming exercises & project, reading material, discussion sessions.

F-2 FRI 15.01.2016
Topics: Goals, plans, knowledge, agents, tasks & environments

Note: Assigned readings should be read before class. Alternatively, as a less desirable alternative, readings may be read after class. Reading the assigned readings not at all should generally be avoided.


W2 JAN

F-3 TUE 19.01.2016
Overview of key concepts
Reinforcement learning

F-4 FRI 22.01.2016
Systems & Architectures, good old-fashioned AI, control theory
Review of Programming Assignment 1


W3 JAN

F-5 TUE 26.01.2016
Requirements for artificial general intelligence
Artificial general intelligence, features of intelligence, architecture

F-6 FRI 29.01.2016
Features of (artificial) general intelligence
Review of Programming Assignment 2


W4 FEB

F-7 TUE 02.02.2016
Tasks, environments, goals: A second look

  • Readings assigned for this class (read before lecture):
    • No new readings - please catch up on unread assigned readings! And start reading next class' papers.

F-8 FRI 05.02.2016
Evaluating AIs
Review of Programming Assignment 3


W5 FEB

F-9 TUE 09.02.2016
Agents & environments: Take two

F-10 FRI 12.02.2016
Review of programming project 3
Discussion of questions posted on Piazza


W6 FEB

F-11 TUE 16.02.2016
Agents & models
Meaning and symbols, part I

F-12 FRI 19.02.2016
Constructionist versus constructivist methodology
Discussion of reading assignment questions posted on Piazza


W7 FEB

F-13 TUE 23.02.2016
Constructivist methodology

F-14 FRI 26.02.2016
Semiotic circularity, emergence, auto-catalysis
Discussion of reading assignment questions posted on Piazza


W8 MAR

F-15 TUE 01.03.2016
Attention

F-16 FRI 04.03.2016
Reasoning
Discussion of reading assignment questions posted on Piazza


W9 MAR

F-17 TUE 08.03.2016
Metacognition / Integrated Cognitive Control and self-programming

F-18 FRI 11.03.2016
Seed-AI
Discussion of reading assignment questions posted on Piazza


W10 MAR

F-19 TUE 15.03.2016
Creativity, consciousness and emotions

F-20 FRI 18.03.2016
NARS


W11 MAR

F-21 TUE 22.03.2016
Universal Pedagogy

F-22 FRI 25.03.2016 NO CLASS - EASTER HOLIDAY


W12 MAR / APR

F-23 TUE 29.03.2016 NO CLASS - EASTER HOLIDAY

F-24 FRI 01.04.2016
Review of Programming Assignment 4
AERA


W13 APR

F-25 TUE 05.04.2016
Review of Programming Assignment 5

F-26 FRI 08.04.2016
Student presentation of Programming Assignment 5
Short review and summary of course material and Final Exam




EOF

/var/www/ailab/WWW/wiki/data/pages/public/t-720-atai/atai-16/main.txt · Last modified: 2016/03/31 13:46 by thorisson2