UNIT OVERVIEW CITS4404 Artificial Intelligence & Adaptive Systems.

Slides:



Advertisements
Similar presentations
Approaches, Tools, and Applications Islam A. El-Shaarawy Shoubra Faculty of Eng.
Advertisements

LECTURE SERIES on STRUCTURAL OPTIMIZATION Thanh X. Nguyen Structural Mechanics Division National University of Civil Engineering
Welcome to the HSC Study Day For Science. Session Outline  The Content  The Syllabus  The Biggest Secret of All!  The Biggest Mistake of All!  The.
Two e-Learning elective seminars in Novi Sad Putnik Z., Komlenov Ž., Budimac Z. DMI, Faculty of Science University of Novi Sad.
CS 346U Exploring Complexity in Science and Technology Instructor: Melanie Mitchell Textbook: M. Mitchell, Complexity: A Guided Tour (Oxford University.
Business Modelling for Internet Based Technology Intro Lecture §Recap on Unit Aims §Unit Study Plan l lectures l tutorials l Resources §Unit Assessment.
Project Workshops Project Oral. 2 Supervisor plus one other member of academic staff Between final paper submission and exams (usually weeks 21-22) Maximum.
CSE 322: Software Reliability Engineering Topics covered: Course outline and schedule Introduction, Motivation and Basic Concepts.
Course Introduction (Lecture #1) ENGR 107 – Intro to Engineering The slides included herein were taken from the materials accompanying Engineering Fundamentals.
Computer Science ABET Visit Update November 8, 2003.
COMP-6600: Artificial Intelligence (Overview) A tentative overview of the course is as follows: 1. Introduction to Artificial Intelligence 2. Evolutionary.
1 The Teaching and Learning Strategy, including Projects Roy Crole Department of Computer Science University of Leicester.
Introduction to Artificial Neural Network and Fuzzy Systems
INTRODUCTION TO COMPUTATIONAL INTELLIGENCE, Nanjing University Spring 2014 INTRODUCTION TO COMPUTATIONAL INTELLIGENCE Lin Shang Dept. of Computer Science.
New experiences with teaching Java as a second programming language Ioan Jurca “Politehnica” University of Timisoara/Romania
Teaching Teaching Discrete Mathematics and Algorithms & Data Structures Online G.MirkowskaPJIIT.
Computer Network Fundamentals CNT4007C
Student Centered Teaching Through Universal Instructional Design Part III.
이화여자대학교 교육대학원 1 Getting Participation Through Discussion - Martyn Clark - School of Computer Studies University of Leeds 성명 : 홍 승 희 전공 : 컴퓨터교육 학번 : 002CSE10.
CI TECHNOLOGIES CITS4404 Artificial Intelligence & Adaptive Systems.
CS 346U Exploring Complexity in Science and Technology Instructor: Melanie Mitchell Textbook: M. Mitchell, Complexity: A Guided Tour (Oxford University.
IT 499 Bachelor Capstone Week 8. Adgenda Administrative Review UNIT Seven UNIT Eight Project UNIT Nine Preview Project Status Summary.
Final Year Project COMP390/393/394/395 Irina Biktasheva – coordinator
WXGE 6103 Digital Image Processing Semester 2, Session 2013/2014.
CISB594 – Business Intelligence
COMPE 564/ MODES 662 Natural Computing 2013 Fall Murat KARAKAYA Department of Computer Engineering.
Conceptual Foundations © 2008 Pearson Education Australia Lecture slides for this course are based on teaching materials provided/referred by: (1) Statistics.
New Advanced Higher Subject Implementation Events Engineering Science Advanced Higher Course Assessment.
Jonathan St Clair Computer Science Honours 2003 Supporting harvest prediction using artificial intelligence techniques Jonathan St Clair STCJON003
TGP2281: Game Programming III also better known as Game AI.
Computational Intelligence II Lecturer: Professor Pekka Toivanen Exercises: Nina Rogelj
Goran Šuković, University of Montenegro 1/24 Experiences with Diploma Projects at University of Montenegro 10 th Workshop on “Software Engineering Education.
CS 445/545 Machine Learning Winter, 2012 Course overview: –Instructor Melanie Mitchell –Textbook Machine Learning: An Algorithmic Approach by Stephen Marsland.
16469 Low Energy Building Design 2010 Dr N J Kelly.
Most of contents are provided by the website Introduction TJTSD66: Advanced Topics in Social Media Dr.
Multimedia Games Development COM429 Demo and presentation Week 12 Assignment 3.
CITS7212: Computational Intelligence An Overview of Core CI Technologies Lyndon While.
Information Systems in Organizations Introduction instructor’s name.
Reinforcement Learning AI – Week 22 Sub-symbolic AI Two: An Introduction to Reinforcement Learning Lee McCluskey, room 3/10
Mr C Johnston ICT Teacher G041: How Organisations Use ICT Introduction To The Unit.
MITM613 Wednesday [ 6:00 – 9:00 ] am 1 st week. Good evening …. Every body.
Advances in Cloud Computing CIS6930/CIS4930
CITS7212: Computational Intelligence Welcome to CITS7212 CITS7212: Computational Intelligence Lyndon While.
Computer Networks CNT5106C
1 Sobah Abbas Petersen Adjunct Associate Professor, NTNU Researcher, Sintef TDT4252 Modelling of Information Systems Advanced Course TDT4252,
HRM 498 ASSIST Teaching Effectiverly/hrm498assist.com FOR MORE CLASSES VISIT
FNA/Spring CENG 562 – Machine Learning. FNA/Spring Contact information Instructor: Dr. Ferda N. Alpaslan
Course Overview Stephen M. Thebaut, Ph.D. University of Florida Software Engineering.
CS 664 Sample Presentation
Final Year Project COMP390/393/394/395
Computer Network Fundamentals CNT4007C
Advanced Software Engineering
Final Year Project COMP390/393/394/395
CITS4404 Artificial Intelligence & Adaptive Systems
Computer Networks CNT5106C
Introduction to CS Senior Design Project I / II
RESEARCH APPROACH.
Artificial Intelligence (CS 461D)
CPSC 441: Computer Communications
Introduction to CS Senior Design Project I / II
Introduction to CS Senior Design Project I / II
Computer Networks CNT5106C
KBSR: AIMS & OBJECTIVES
Centre for Emergent Computing
Introduction to Neural Networks and Fuzzy Logic
Introduction to Neural Networks and Fuzzy Logic
Introduction to CS Senior Design Project I / II
Computer Networks CNT5106C
CS 6640 Sample Presentation
Technologies of Google Seminar Week 1
Presentation transcript:

UNIT OVERVIEW CITS4404 Artificial Intelligence & Adaptive Systems

2 Unit overview Artificial Intelligence Adaptive Systems Computational Intelligence Nature-inspired, heuristic-based technologies, that demonstrate emergent, adaptive, or intelligent behaviour

3 Contd. Nature-inspired : ideas taken from observations of natural systems Heuristic-based : solutions constructed using guidelines, estimates, trends, … Emergent behaviour : systems behave in ways that aren’t or can’t be predicted in advance Adaptive behaviour : systems behave differently depending on contextual or environmental factors Intelligent behaviour : ??

4 Contd. CITS4404 will introduce several core CI technologies Evolutionary algorithms Particle swarm optimisation Ant colony optimisation Neural networks These are “heavyweight” technologies, usually applied to Complex optimisation problems Adaptive learning Knowledge acquisition Applying these technologies is not like calling quicksort! Learning classifier systems Artificial immune systems Fuzzy reasoning Bayesian reasoning

5 Reading units CITS4404 is a reading unit We will not teach you the material We will assist you in learning the material The emphasis is on self-learning and self-investigation, where students find and apply information themselves You should still expect to average 10–12 hours/week, as normal for a 6-point unit

6 Unit structure Three lectures that introduce The CI concept The technologies Practical issues Students are then divided into groups of 2–4 people Each group is assigned one of the CI technologies and they Present a seminar on their technology Present a seminar on an application of their technology Conduct a group project applying their technology to a given problem All students are expected to develop a basic understanding of all the technologies in the unit One final lecture on local research in the CI area

7 Background research All students will be given some introductory references on each technology These papers will introduce/summarise the topic, but they will be insufficient for a complete understanding Each group is expected to research their technology in more detail than provided by these papers

8 The group seminars First seminar in Weeks 5–6 on the group’s technology Second seminar in Weeks 8–9 on an application Seminars should run for 25 minutes plus 5 minutes questions Do not assume any prior knowledge of the technology Maintain a balance between overview and technical details Ideas should build upon each other successively Pictures, diagrams, videos, and demos are all good!

9 Contd. Seminars will be assessed on Understanding of the technical material Breadth of coverage Quality of the presentation All group members should contribute to all aspects Don’t be afraid to include other people’s material But all such material should be attributed properly Slides should be ed to the coordinator after the seminar

10 The project The project will be introduced in Week 9 Groups will apply their technology to a real-world problem chosen by them as suitable for that approach Week 10: groups present their chosen problem to the class Week 13: groups present their results to the class Week 14 (swotvac): written submission due A report on your chosen problem Its solution using your technology The structure, implementation, and performance of your solution Again, all group members should contribute to all aspects More details on the project will be released in due course

11 Unit assessment Two main seminars in Weeks 5–9, each worth 15% The project deliverables, collectively worth 40% A final exam in November, worth 30%