The document describes opportunities for Honours projects in 2007 at the Computer Sciences Lab and NICTA. It discusses four research groups focused on areas like artificial intelligence, machine learning, logic and computation, and computer vision. Each group has several potential project topics listed, such as planning under uncertainty, constraint satisfaction, document analysis, and verified microkernel development. Contact information is provided for over 15 specific projects that students could get involved in.

1. Computer Sciences Lab & NICTA
Opportunities for Honours projects 2007
Sylvie Thiebaux

2. College of Engineering & Computer Science (& Friends)
DCS
DEng
CSL
InfoEng
NICTA

3. Research Groups
• Research focuses on:
– Artificial Intelligence
– Logic & Automated Reasoning
– Computer Vision
• 40 researchers in 4 groups:
– Diagnosis, Planning, & Optimisation (DPO, aka KRR)
– Statistical Machine Learning (SML)
– Logic & Computation (LC)
– Vision Science, Technology & Applications (VISTA)

4. Diagnosis, Planning & Optimisation Group
• Diagnosis
– Explain abnormal situations from observations
– Circuits, power networks, web services, humans
• Planning
– Decide & schedule the tasks to be undertaken
to meet given objectives
– Project planning, military operations planning,
robot control, solving puzzles & games
• Optimisation
– Find the best possible solution to a problem
– How can we predict the hardness of optimisation problems?
Contact: Sylvie.Thiebaux@anu.edu.au

5. Planning with time, resources, and uncertainty
• Uncertainty about task duration
and resource consumption
– Model uncertainty
– Handle continuous time/res.
– Design efficient algorithms
– Build robust plans
– Build better GUIs
• Build a better Microsoft Project! Contact: Doug.Aberdeen@nicta.com.au

6. Model-Based Supervision of Composite Systems
Composite systems:
feature simple components organised into a
highly reconfigurable architecture
Examples:
web & grid services, power and water systems
telecom networks, traffic control systems
Supervision tools: confer the ability to
– self-diagnose to detect faults in the
system and explain their causes
– self-reconfigure to restore or improve
service
Project goals: develop theories, algorithms &
tools for the supervision of composite systems
Approach: draws on artificial intelligence
(model-based diagnosis, planning), discrete-
event systems, and model-checking
Contact: Sylvie.Thiebaux@anu.edu.au

7. Statistical Machine Learning Group
• Machine Learning automates the input-output mapping.
• Lots of fun projects for analysing data.
Let us do both theory and application
input(data)
Documents
Video
Molecules
Microarrays
Sensor Networks
Mission Plans
output(analysis)
Authors, script
People, scenes
Biological function
Cancer diagnosis
Novelty, alarm
Optimal strategy
Magic happens …
Contact: Alex.Smola@nicta.com.au

8. Bioniformatics
• Build feature selector for genes
• Integrate sequencing information (similarity ..)
• Integrate automatic analysis of abstract
+ =
Cancer diagnosis
Contact: Adam.Kowalczyk@nicta.com.au

9. Document Analysis
ab
c$
b
c$c$abc$ abc$
+
.
• Build document similarity measure
• Build fast discriminative optimiser (SVM style)
• Integrate into mail filtering system (e.g. DSPAM)
= Spam filter
Suffix tree
Contact: SVN.Vishwanathan@nicta.com.au

10. Logic and Computation Group
• Logical analysis of systems
– Assure correctness, safety, robustness
– Software systems (are votes counted okay?)
– Physical systems (will the robot arm break?)
– Systems of agents (can I trust this eBay seller?)
• Tools for reasoning by computers
– Logical deduction: “Does it follow?”
– Constraint satisfaction: “How might it be?”
• Theory behind all this
– New kinds of logic for new tasks
Contact: John.Slaney@anu.edu.au

11. Constraint Satisfaction Platform (G12)
• Constraint Satisfaction Problem
– “Hard” constraints - e.g. every team
plays every other at home and away
– “Soft” constraints - e.g. fairness
conditions (may be complex)
– Additional requirements from TV
stations, etc. complicate further
• Difficult computational problem
Contact: John.Slaney@anu.edu.au

12. L4 Verified
L4 Micro-kernel
L4 operating system used in embedded systems
e.g. sensor networks, mobile phones
“Small” trusted kernel (guarantees separation properties)
NICTA project: formally verify the kernel
Project runs until 2008
One of the most ambitious formal verification projects ever
undertaken anywhere
Commercial potential if successful
Contact:
Michael.Norrish@nicta.com.au

13. Vision Science, Tech. & Applications Group
• Major projects:
– Spectral imaging
– Smart cars
– Medical image analysis
– Surveillance
Contact: Nick.Barnes@nicta.com.au

14. Smart Cars
Pedestrian detection & tracking
Speed sign detection & recognition
Car detection & tracking
A complete driver assistance system, focusing on driver safety
Contact: Lars.Petersson@anu.edu.au

15. Automatic Anatomical Structure Extraction
Topology repair Parametrisation
Detection of Alzeihmer’s disease
- changes to hyppocampus implicated
- doctors hand-trace each scan slice
- obtain a math. representation for analysis
- need to repair and parametrise the 3D data
Contact: Paulette.Lieby@nicta.com.au

16. Finally …
• These slides are at: http://rsise.anu.edu.au/~thiebaux/HP.ppt
• Many other projects, for exmple in:
• Traffic control Philip.Kilby@anu.edu.au, Doug.Aberdeen@nicta.com.au
• Game playing Adi.Botea@nicta.com.au, Nic.Schraudolph@nicta.com.au
• Sensor networks Alex.Smola@nicta.com.au
• Agent architectures John.Lloyd@anu.edu.au
• Artificial AI, Trust Jochen.Renz@anu.edu.au
• Automated deduction Rajeev.Gore@anu.edu.au, John.Slaney@anu.edu.au
• Satisfiability Anbulagan@nicta.com.au, Jinbo.Huang@nicta.com.au,
Jussi.Rintanen@nicta.com.au
• If you like theory Tomasz.Kowalski@anu.edu.au
• Apply for a summer scholarship with us!