1 / 20

Research Information Session

Research Information Session. Associate Professor John Thornton Gold Coast BIT Honours Degree Convenor and Research Higher Degree Coordinator J.Thornton@griffith.edu.au. ICT Research at Griffith. Staff at the School of ICT are both active researchers as well as teachers

gerald
Download Presentation

Research Information Session

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Research Information Session Associate Professor John Thornton Gold Coast BIT Honours Degree Convenor and Research Higher Degree Coordinator J.Thornton@griffith.edu.au

  2. ICT Research at Griffith • Staff at the School of ICT are both active researchers as well as teachers • We have world-class concentrations of researchers in several key areas, for example: • Artificial Intelligence and Robotics • Complex Systems • Speech and Image Processing • The Institute for Integrated and Intelligent Systems (IIIS) Research Centre unifies our research groups and is regarded as one of the strongest ICT research concentrations in the Australian University system John Thornton

  3. How You Can Get Involved • Do well at your studies! • Transfer to the BIT Advanced and get involved in supervised projects before you graduate • Take advantage of summer scholarships that enable to work on a range of research projects • Think about what you might like to research in the future and take courses that are relevant • Enrol in a 4th year of Honours study at the end of your degree John Thornton

  4. About the Honours Degree • Must have GPA of 5.0 (credit) or better for 2nd and 3rd year of Bachelor degree • One year full-time – 80CP made up of: • 40CP Dissertation • 10CP Research Methods in IT + 30CP electives • Up to one 3rd year course • Rest must be honours level • Supervisor may run a special subject • Graded 1st, 2.1, 2.2 or 3rd class John Thornton

  5. Choosing a Research Topic • Honours is about research training • Find a topic that interests you • Find a supervisor you can work with • Consider your future after honours • Entry into a more interesting job? • Research Higher Degree, e.g. PhD? • Career as an academic? • Your choice of topic and supervisor sets the direction of your future life – consider carefully – getting 1st class also matters John Thornton

  6. Financial Support • University values its research students • Your work and publications raise the university’s profile • Various School Scholarships: • Summer Project $2,000 • Honours Scholarship $2,000 • Other sources: • IIIS, NICTA, Supervisor Funds • Tutoring opportunities John Thornton

  7. After Honours • Honours equips you for entry into a PhD where you can spend 3 years researching (to your heart’s content) in a chosen area • From there you can pursue a career as a researcher or as an academic • During a PhD, if you have done well at honours, you can expect to gain a full scholarship (around $20,000 pa) and if you are an Australian resident then there are no fees • You can also expect to get part-time work teaching • Otherwise Honours equips you to enter the workforce at a higher level, with specialist knowledge and research skills John Thornton

  8. Research with Dr John • Gold Coast Honours Convenor • Associate Director IIIS for Gold Coast • RHD Coordinator IIIS and ICT Gold Coast • NICTA researcher • Leader of Constraint Satisfaction and Hierarchical Temporal Memory research groups • 8 PhD completions • 1 MPhil, 2 Masters, 5 Honours completions John Thornton

  9. What are Constraints? A constraint is a relationship over object(s) in the world. What is allowed? What is not allowed? Knowledge about broad range of real world domains can be easily expressed in terms of constraints John Thornton

  10. Constraint Programming “Constraint programming represents one of the closest approaches computer science has yet made to the Holy Grail of programming: the user states the problem, the computer solves it.” Eugene Freuder, Constraints, April, 1997. John Thornton

  11. Constraint Satisfaction • Given: • A set of variables • A set of permitted values for each variable • A set of constraints on subsets of variables Find: an assignment of values to variables such that all the constraints are satisfied. John Thornton

  12. Example: Graph Colouring • Variables: geometric regions (e.g., all states in India) • Domain: available colours • Constraints: neighbours cannot have the same colour John Thornton

  13. General Techniques • Problems are often NP-complete • Over-constrained • Two classes of technique: • Backtracking • Local search John Thornton

  14. Eight Queen Problem Domain Variable Constraint John Thornton

  15. Place 8 Queens randomly on the board 3 2 2 1 1 1 3 3 0 1 2 2 3 4 3 1 2 2 2 2 2 3 1 1 2 Answer Found Pick a Queen: Calculate cost of each move Take least cost move then try another Queen 1 2 1 2 1 3 2 3 1 4 1 5 1 0 1 1 1 3 1 4 1 0 1 4 1 4 1 4 1 2 3 1 1 1 3 1 4 3 2 1 3 3 1 4 2 2 2 1 3 2 2 2 2 2 3 2 2 2 3 1 2 4 3 1 3 1 1 2 2 2 1 1 2 1 2 3 3 2 3 0 2 2 3 3 3 3 3 3 4 1 Local Search John Thornton

  16. Selected Results • Building Structure into Local Search for SAT • IJCAI’07 Distinguished Paper Award • Winner of SAT Competition Gold Medals • gNovelty+ (2007), R+AdaptNovelty+ (2005) • Temporal Reasoning • Local Search (JLC), New SAT encoding (CP’06) • Hybrid Search • Resolution + SLS (AAAI’05) • Evolving Algorithms for CSPs • Genetic programming (CEC’04, PRICAI’04) John Thornton

  17. Research Challenges • Parameter free clause weighting local search (for SAT competition) • Exploiting structure (dependency lattice) • Local search method for UNSAT problems (IJCAI’97 challenge problem) • Methods for solving problems in non –CNF form (bio-informatics, model checking) • Handling over-constrained problems • Transforming complex problems into CSPs/SAT John Thornton

  18. New Research Directions • Hierarchical Temporal Memory • Using insights from computational neuroscience to build more robust and flexible pattern recognition machines • Exploiting temporal connections between inputs (temporal pooling) • Combining recognition with prediction John Thornton

  19. The Teams IIIS CSP/SAT:Abdul Sattar, Wayne Pullan, Duc Nghia Pham, Stuart Bain, Lingzhong Zhou, Matthew Beaumont, Valnir Ferreira Jr. Abdelraouf Ishtaiwi NICTA CSP/SAT: Michael Maher, Charles Gretton, John Slaney, Anbulagan IIIS HTM:Michael Blumenstein, Trevor Hine, Jolon Faichney, Richard Speter John Thornton

  20. Thank You Questions? (also see www.cit.gu.edu/~johnt/) John Thornton

More Related