NTNU Norges teknisk-naturvitenskapelige universitet
  Fakultet for informasjonsteknologi, matematikk og elektroteknikk > Institutt for datateknikk og informasjonsvitenskap

IT3708 - Subsymbolic Methods in AI, Spring 2014

Contents
  • Home

  • News

  • Schedules

  • Lectures

  • Curriculum

  • Assignments

  • Grading

  • Previous Exams

  • Mailing list

  • IT8008 for PhD's

  • Links


  • On these pages you will find relevant static information regarding the course.

    We will use It's Learning for several aspects of the course, including student uploading of projects and essays. However, most course materials such as lecture notes, supplementary literature and homework assignments will only be available at THIS website. In addition, the instructor uses the it3708 mailing list (and not necessarily It's Learning) for important course announcements, so please subscribe to that list as soon as possible.

    To correspond with Keith Downing, the course instructor, please use email (see address below). Keith does NOT use It's Learning for mail.

    Lecture Meetings

    Tuesdays 12:15 - 14:00 (Hovedbygget H1, which also has room number 116)

    Office Hours for February and (at least part of) March (Room 308 or 313 IT-Vest)

    Monday and Thursday (9:00 - 11:00)

    Course Overview

    This course introduces several artificial intelligence methods that draw considerable inspiration from biology and tend to involve more quantitative calculation than symbol manipulation. Hence, common umbrella terms for these methods include Sub-symbolic and Bio-Inspired . Examples include evolutionary algorithms (EAs), artificial neural networks (ANNs), swarm intelligence , artifical development and artificial immune systems (AIS).

    This year (2014), the course will begin with a focus on Swarm Intelligence (in particular, Swarm Robotics) for the first three lectures. EAs and ANNs will then be covered in the remainder of the course.

    Swarm robotics is a field that capitalizes on self-organization to generate interesting global patterns from interactions among relatively simple robots, all in the absence of centralized control. This embodies a physical form of distributed problem-solving that is one of the signature application areas of the field of Artificial Life (ALife).

    EAs use the evolutionary biological metaphor of Darwinian natural selection as the basis for stochastic parallel search through complex fitness landscapes. This powerful search technique has been applied to a host of problem domains, such as task-scheduling, controller design, pattern recognition, robotics, immunology, economics and machine learning. In addition, EAs are commonly used in artificial life (alife), an exciting new interdisciplinary area with strong connections to biology, chemistry, mathematics, computer science and engineering. We will focus on two types of EAs: genetic algorithms (GA) and genetic programming (GP).

    Neural networks are powerful machine-learning tools abstractly based on the behaviors of collections of neurons in the brain. They are exceptionally useful in learning general concepts from examples, in either a supervised mode (i.e. the system is told which class each example belongs to) or unsupervised situations, where the ANN has to cluster the examples based on similarity. The distributed nature of information in neural networks makes them fundamentally different from standard AI knowledge representations and very popular as models of memory and as tools for complex data-analysis tasks in a wide variety of domains.


    People

    Lecturer and coordinator: Keith Downing(keithd<at>idi.ntnu.no)
    Office: Room 308 IT-Vest

    Post-Doctoral Lecturer and Teaching Assistant: Jean-Marc Montanier (jean-marc.montanier<at>idi.ntnu.no)
    Office: Room 356 IT-Vest

    Undergraduate Teaching Assistants:
    • Hege Beate Seilen (seilen<at>stud.ntnu.no)
    • Joachim Halvorsen (joachha<at>stud.ntnu.no)
    Help Hours: (to be determined)
    Redaktør: Kontorsjef Bård Kjos  Kontaktadresse: Pauline Haddow  Sist oppdatert: 01.01.1970