Research interests:

Probabilistic graphical models, Bayesian statistics, Gaussian processes, transfer learning, and applications to computer systems problems, document analysis and dynamical systems.

Research interests:

AI planning, heuristic search, games, path planning

Duties:

Affiliated with: The Optimization Research Group at NICTA, Canberra; and The Artificial Intelligence Group at the Computer Science Laboratory, Australian National University, Canberra.

Research opportunities with Dr Adi BOTEA

• Achieving diagnosability by AI planning, with application to the Smart Grid

No Image Available

Research interests:

Topic models and non-parametric methods for text analysis. More generally, theoretical and applied work in machine learning, probabilistic methods, graphical models. See more at my NICTA website.

Bio:

Undergraduate in mathematics and MQual (1st class) in Computer Science at University of Queensland, PhD. in the area of machine learning in 1992 at UTS (Sydney), and a Docentship at University of Helsinki in 2006. Been on committees and/or reviewing for AAAI, ACML, IJCAI, UAI, KDD, COLT, ICML, ECML-PKDD, NIPS, Discovery Science, AI and Statistics, SIGIR, CIKM, ECIR, WSDM and WWW.

Research opportunities with Dr Wray BUNTINE

• Automated Hierarchical Classification of Web Pages or Documents
• Developing Elaborate Topic Models
• Linguistic Topic Models
• Latent Probabilistic Analysis/Inference on Text
• Unsupervised Part-of-Speech Training with Non-parametric Methods

Research interests:

Pattern Recognition, Machine Learning, Computer Vision.

Bio:

I am a Senior Researcher at NICTA's Canberra Laboratory, where I am a member of the Statistical Machine Learning research group. I am also affiliated to the Australian National University as an adjunct research fellow in the Research School of Information Sciences and Engineering.

Before joining NICTA in January 2005, I have been a post-doctoral fellow for a few months in 2004 with the AICML at the University of Alberta, Canada, where I worked with Dale Schuurmans.

I wrote my PhD thesis in the area of structural pattern recognition. I was supervised by Terry Caelli and Dante Barone. The defense took place in Porto Alegre on July 2004.

Prior to starting my PhD, I worked three years for a Nuclear Medicine company (ADAC Laboratories), which was later bought by PMS. As an undergraduate I did research in theoretical physics with Felipe Rizzato.

Research interests:

Probabilistic Graphical Models, Machine Learning, Computer Vision

Research opportunities with Dr Justin DOMKE

• Comparison of Classification-Based Loss Functions
• Multiscale Conditional Random Fields for Scene Recognition

Research interests:

I have broad interests in computer and robotic vision, machine learning, probabilistic graphical models, and discrete and continuous optimization. My main research is in the application of machine learning techniques (specifically, conditional Markov random fields) to geometric and semantic scene understanding.

I am always looking for motivated students who are interested in doing research with me. I encourage ANU students to contact me about undergraduate or PhD research projects. Students outside of ANU who are interested in doing a PhD with me should read the following documents before contacting me.

• Pre-application process
• Formal application process

Research opportunities with Dr Stephen GOULD

• Machine Learning with Structured Representations in a Dataflow Framework
• Machine Learning and Computer Vision Software Framework
• Image Segmentation and Scene Understanding
• Artificial Intelligence for playing video games

Research interests:

My main research topic is the diagnosis of discrete-event systems. The basic idea is the following. Consider a system (for instance a machine, such as a computer, a car, a space robot, or machine in a factory, etc.) which performs some actions. The system is subject to faults (such as short-circuit, leaking, break of a component, etc.) which leads to an uncorrect behaviour of the system. The goal is to use the observations (alarms generated by the system, informations provided by sensors, etc.) on the system find out what happened on the system. More precisely, I am interested in discrete-event systems. Such systems are so that their behaviour is not continuous but can be modeled as a discrete evolution (by events). A set of behaviours on such a system can be represented by an automaton. For instance, the model is often an automaton (or an equivalent representation). I often define the diagnosis as the computation of all the possible behaviours on the system consistent with the observations. This can also be represented by an automaton. The problem is quite well defined, and the main issue is the complexity which is exponential in the number components in the system.

Duties:

I currently hold a position of researcher level B at NICTA, at the Research School of Information Sciences and Engineering. I am working on the SuperCom project: supervision of composite systems. I also do some teaching: AI and Advanced AI courses.

Bio:

I got a Master degree in 2002 in Computer Science(fr) from the INSA de Rennes (fr) (National Institute of Applied Science). The same year, I got a DEA (Master degree more dedicated to researcher).

I worked with Pierre-Yves Glorennec during summer 2001 on fuzzy logic and regression tree.

I did my Master thesis under the supervision of Marie-Odile Cordier and Christine Largouet on the topic of using model-checking techniques to solve diagnosis problems. In October 2002, I started my PhD under the supervision of M-O Cordier and Ch Largouet on decentralised and incremental diagnosis of reconfigurable discrete-event systems. I worked with two roommates: Elisa Fromont (mostly fr) and Francois Portet. I defended my thesis one week after them (grumpf!) in December 2005. During my PhD and my Master, I did some teaching (introduction to algorithmic, advanced course on compilation, artificial intelligence).

Research opportunities with Dr Alban GRASTIEN

• Achieving diagnosability by AI planning, with application to the Smart Grid
• Diagnosis of discrete event systems by SAT
• Diagnosis properties as a game
• An FDI-inspired approach to diagnosis of DES
• Chronicles vs. Conflicts vs. ARR
• Diagnosis of Discrete Event Systems by Petri Nets and Integer Linear Programming
• Optimal Compressed Path Databases for Ultra Fast Path Finding in Maps

Research interests:

I am a computer scientist who works in a sub-field of Artificial Intelligence called Automated Planning. Although my interests extend to other subjects in Machine Learning and Automated Reasoning, my expertise lies mostly within planning. My goal is to study and develop planning technology that will allow machines (i.e., robots and computers) to reason about deliberations in their world, and to reason about how to extend their own model of the world intelligently. Specialties: decision-theoretic planning, non-Markovian rewards, probabilistic planning, relational reinforcement learning, SAT-based deterministic/classical and probabilistic planning

Duties:

Research, Lecturing, Student Supervision (PhD, Masters, and Honours), and Grant Writing.

Bio:

I joined the NICTA lab and CECS at ANU in Canberra in August of 2011. I am working at the intersection of Artificial Intelligence and Operations Research on solutions to fleet logistics problems. I was a research fellow with the Intelligent Robotics Lab at the University of Birmingham 2008-2011; There I worked on a project investigating cognitive robots that could self-understand and self-extend.I was a researcher with the NICTA lab in Brisbane 2006-2008; There, I worked on fundamental research in AI Search, and simulation studies of city wide evacuation planning. I am the primary author of NRMDPP, runner up in the probabilistic track of the 2004 International Planning Competition. Co-author of ayPlanAgain, runner up in the multi-core track of the 2011 International Planning Competition. Co-author of best paper at the 2010 Pacific Rim International Conference on Artificial Intelligence. Co-author of gNovelty+, winner of the "Random" category at the 2007 International SAT competition. I have held an adjunct position with Griffith University since 2006. I have supervised a number of undergraduate students and visiting PhD students. Those include Dr Muhammad Shah (2011), Mayank Jain (2008), Acku Chauhan (2008), and Dr Aditi Barthwal (2003/04). I supervised a number of graduated PhD students, including Griffith University IIIS students Silvia Richter, and Nathan Robinson -- Dr Richter was awarded the 2012 John Makepeace Bennet Award for the best Australasian Doctoral Dissertation.

Research opportunities with Dr Charles GRETTON

• Geometric Soft-Constraints for Pragmatic Vehicle Routing
• Stochastic Local Search for SAT Encodings of Planning Problems
• Decision-Theoretic Planning via Boolean Satisfiability
• Artificial Intelligence for playing video games

No Image Available

Research interests:

For details concerning my research interests & publications, student project topics, and some pictures of random trees, please see http://users.rsise.anu.edu.au/~patrik/.

Research opportunities with Dr Patrik HASLUM

• Projects in Automated Planning
• Various Combinatorial Optimisation Problems
• Planning a Story
• Computing Optimal Genome Edit Distances via Heuristic Search
• Efficient Cost-Bounded Search and Planning
• Stochastic Local Search for SAT Encodings of Planning Problems

Research interests:

Mixed-Integer Nonlinear Programming

Bio:

Hassan Hijazi received a Ph.D. in Computer Science from the Universitée de La Méditerranée at Marseille while working at Orange Labs - France Telecom R&D from 2007 to 2010. He then joined the Optimization Group at the Computer Science Laboratory of the Ecole Polytechnique. Currently, Hassan Hijazi holds a researcher position in Canberra Research Lab at National ICT Australia and is an adjunct research fellow at the Australian National University (ANU). His main field of research is mixed integer nonlinear programming and applications in network based problems, where he has given contributions both in theory and practice.

Research interests:

Dr Huang is a senior researcher at NICTA (Managing Complexity Research Group), with an adjunct appointment in the Research School of Computer Science at the Australian National University. His research interests include logical and probabilistic reasoning and their applications, and artificial intelligence in general. He completed his PhD in 2005 in the Computer Science Department at the University of California, Los Angeles as a member of the Automated Reasoning Group.

Dr Huang is available to supervise summer scholar, honors, and PhD projects at the ANU.

Research opportunities with Dr Jinbo HUANG

• Finding Minimal Unsatisfiable Subsets in Temporal Logic

Research interests:

Artificial intelligence, Bayesian statistics, theoretical computer science, machine learning, sequential decision theory, universal forecasting, algorithmic information theory, adaptive control, MDL, image processing, particle physics, philosophy of science.

Bio:

Marcus Hutter is Professor in the RSCS at the Australian National University in Canberra, Australia. He received his PhD and BSc in physics from the LMU in Munich and a Habilitation, MSc, and BSc in informatics from the TU Munich. Since 2000, his research at IDSIA and now ANU is centered around the information-theoretic foundations of inductive reasoning and reinforcement learning, which has resulted in 100+ publications and several awards. His book "Universal Artificial Intelligence" (Springer, EATCS, 2005) develops the first sound and complete theory of AI. He also runs the Human Knowledge Compression Contest (50'000€ H-prize).

Research opportunities with Professor Marcus HUTTER

• Universal Artificial Intelligence (UAI)
• Human Knowledge Compression Contest (HKCC)
• On the Foundations of Inductive Reasoning (FIR)
• Generic Reinforcement Learning Agents (GRLA)
• Mathematical Foundations of Artificial Intelligence (MFAI)
• Choose Your Own Project (CYOP)
• Modelling non-Gaussian spatio-temporal environmental data CSIRO PhD top-up $15000 per year available for application
• Unifying Probability and Logic for Learning (UPL)

Research interests:

• Operations Research
• Combinatorial Optimization
  • Travelling Salesman Problem
  • Vehicle Routing Problem
  • Scheduling
• Graph Algorithms
• Shortest Path Problems
• Assignment Problems


• Artificial Intelligence
• Search
• Constraint Programming

Bio:

Phil received a BSc and his PhD from The University of Queensland, with study mostly in the area of Operations Research. He worked in an Operations Research consulting firm, and then joined CSIRO where he worked in transport and OR fields for more than 10 years. He left as leader of the Operations Research group.

Research opportunities with Dr Phil KILBY

• Geometric Soft-Constraints for Pragmatic Vehicle Routing
• Stochastic Local Search for SAT Encodings of Planning Problems
• Decision-Theoretic Planning via Boolean Satisfiability

Research interests:

Computational logic, agents, declarative programming languages, and machine learning.

Duties:

John Lloyd is a Professor and Deputy Director in the Research School of Computer Science.

No Image Available

Research opportunities with Dr Kee Siong NG

• Research network predictive analytics

No Image Available

Research opportunities with Dr Dirk PATTINSON

• Efficient Compositional Theorem Proving
• Interpolation in Non-Iterative Modal Logics
• Formalised Cut Elimination Proofs
• Implementation of Conditional Logics

Research interests:

My research in machine learning ranges from the theory of statistical and sequential prediction (a.k.a. "online learning") and market mechanisms for learning, to developing protocols for presenting learning algorithms as web services. My aim is to build foundations for wide-spread, machine-assisted prediction.

Duties:

Research Fellow in the Artificial Intelligence Group at the Research School of Computer Science; Contributed to the Machine Learning Group at NICTA.

Bio:

After completing honours in pure mathematics at UNSW I went on to do a PhD in machine learning, also at UNSW. During my PhD I interned at IBM Research in New York and worked as a programmer at Proxima Technology and as a machine learning research engineer at Canon Research, both in Sydney.

Research opportunities with Dr Mark REID

• Useful Games

Research interests:

Artificial Intelligence, knowledge representation, spatial reasoning, temporal reasoning, qualitative reasoning, constraint satisfaction, efficient algorithms, computational complexity, scheduling, operations research, cognitive science, spatial information systems, wireless sensor networks, navigation, trust and reputation, useful games

Bio:

1996: Master's in Computer Science, University of Ulm, Germany
2000: PhD, Albert-Ludwigs University Freiburg, Germany
2000: Postdoc, WITAS lab, University of Linkoping, Sweden
2001-2003: Marie Curie Postdoc Fellow, DBAI, TU Vienna, Austria
2003: Habilitation in Information Systems, TU Vienna, Austria
2003-2006: Researcher at NICTA Sydney, Australia
2006-2008: Fellow at CSL, CECS, ANU, Australia
since 2009: Associate Professor, RSCS, CECS, ANU, Australia
since 2010: ARC Future Fellow, RSCS, CECS, ANU, Australia
since 2011: Head of ANU Artificial Intelligence Group

Research opportunities with Assoc Professor Jochen RENZ

• Efficient Algorithms for Spatial Reasoning
• User friendly navigation with landmarks
• Intelligent Personal Assistants
• Monitoring Geospatial Regions with Intelligent Sensor Networks
• Useful Games
• Artificial Intelligence for playing video games

Research opportunities with Dr Scott SANNER

• Natural Language Query Answering from Wikipedia
• Social Text Mining for Blogs, Tweets and Facebook
• Building Agents that Learn to Play Games
• Mars Rovers and Traffic Controllers
• Scalable Relational Kernels for Data Mining
• Media Geolocation and Google Maps Visualization
• Decision-Theoretic Planning via Boolean Satisfiability

Research interests:

I am working on theoretical foundations for machine learning and AI, in particular for reinforcement learning. Below follows some of my peer-reviewed publications:

Optimistic AIXI, P. Sunehag, M. Hutter, AGI'2012

On ensemble methods for AIXI approximation, J. Veness, P. Sunehag, M. Hutter, AGI'2012

Optimistic Agents are Asymptotically Optimal, P. Sunehag, M. Hutter AusAI'2012

Coding of Non-Stationary Sources ..., P. Sunehag, W. Shao, M. Hutter AusDM'2012

Feature RL using Looping Suffix Trees, M. Daswani, P. Sunehag, M. Hutter EWRL'2012

Context Tree Maximizing Reinforcement Learning, P. Nguyen, P. Sunehag, M. Hutter, AAAI'2012

Asynchronous BCI Using Hidden Semi-Markov Models, G. Oliver, P. Sunehag, T. Gedeon, EMBC'2012

Recursive Channel Selection Techniques for BCI, G. Oliver, P. Sunehag, T. Gedeon, EMBC'2012

Adaptive Context Tree Weighting, A. O'Neill, M. Hutter, W. Shao, P. Sunehag, DCC'2012

Principles of Solomonoff Induction and AIXI, P. Sunehag, M. Hutter Solomonoff Memorial 2011

(Non)Equivalence of Universal Priors, I. Wood.,P. Sunehag, M. Hutter Solomonoff Memorial 2011

Axioms for Rational Reinforcement Learning, P. Sunehag, M. Hutter ALT'2011

Loss functions for improved on-policy control, M. Robards, P. Sunehag, Proc. of EWRL'2011

Feature Reinforcement Learning in Practice, P. Nguyen, P. Sunehag, M. Hutter, Proc. of EWRL'2011

Sparse Kernel-SARSA with an Eligibility Trace, M. Robards, P. Sunehag, S. Sanner, B. Marthi ECML'2011

Consistency of Feature Markov Processes P. Sunehag, M. Hutter ALT'2010

Wearable-sensor activity analysis using semi-Markov models with a grammar O. Thomas, P. Sunehag, G. Dror et al. Pervasive and Mobile Computing 6(3): 342-350, 2010

Semi-markov kmeans clustering and activity recognition from body-worn sensors M. Robards and P. Sunehag ICDM'2009

Variable Metrics Stochastic Approximation Theory P. Sunehag J. Trumpf, S.V.N. Vishwanathan and N. Schraudolph AISTATS'2009

Real method of interpolation on subcouples of codimension one (with S. Astashkin) Studia Math. 185 (2008), 151-168

Using two-stage word frequency models ... P. Sunehag AISTATS'2007

Induced Graph Semantics: Another ... Hammersley-Clifford Thm T. Sears and P. Sunehag MaxEnt'2007

The real interpolation method on couples of intersections (with S. Astashkin) Functional Analysis and Its Applications 40 (2006) 218-221

... Interpolation of operators that almost agree P. Sunehag Journal of Approx. Th. 130 (2004) 78-98

Interpolation Of Banach Algebras And Tensor Products Of Banach Couples (with S. Kaijser) Journal of Mathematical Analysis and Applications 278 (2003) 367-375

Interpolation of Banach algebras and the unit problem. (with S. Kaijser) In: Function Spaces, Interpolation Theory and Related Topics, de Gruyter, Berlin (2002) 345-354.

Bio:

I did my Ph.D. in theoretical mathematics at Uppsala University in Sweden. The topic of the thesis was interpolation of Banach spaces and Banach Algebras. I then worked at NICTA in Canberra Australia as a machine learning researcher. I worked with Document Analysis, Optimization and activity recognition from body-worn sensor. I joined the ANU as a research fellow in July 2009 where I am primarily working on reinforcement learning, particularly on generic reinforcement learning.

Research opportunities with Dr Peter SUNEHAG

• Universal Artificial Intelligence (UAI)
• Generic Reinforcement Learning Agents (GRLA)
• Mathematical Foundations of Artificial Intelligence (MFAI)
• Choose Your Own Project (CYOP)

Research interests:

Machine learning and its applications to health and wellness, mathematical modeling, performance evaluation

Bio:

Dr Hanna Suominen works as a machine learning researcher in the Human Performance Improvement project at NICTA Canberra Research Laboratory, Australia. She also holds an adjunct position in the Australian National University, College of Engineering and Computer Science, Canberra, Australia and is a post doc researcher of the Academy of Finland. Dr Hanna Suominen has a strong expertise in health care services and information systems. Her PhD dissertation on machine learning and clinical text has honours of belonging to the 10 % elite of the field internationally. She has coordinated a Finnish consortium for developing health information and language technology as well as contributed to similar international research networks. She has worked in the Finnish national positron emission centre and taught numerous university courses on bioinformatics and information systems in healthcare. Her other research merits include approximately 35 scientific publications, two best paper awarded contributions, the third prize in the International Medical Natural Language Processing Challenge 2007, Venture Cup 2007-2008 award further funding for research commercialization, and several personal and collaborative research grants (e.g., Academy of Finland, Nordforsk, Tekes). Her language skills include excellent or native English, Finnish and Swedish. Please do not hesitate to contact Dr Suominen for research collaboration or MSc/PhD projects. See http://www.nicta.com.au/people/hanna_suominen for further details and student projects.

No Image Available

Research interests:

Artificial Intelligence: planning, model-based diagnosis, search, and reasoning under uncertainty. For details, see my home page.

Duties:

I am currently NICTA's Canberra Research Laboratory Director.

Research opportunities with Professor Sylvie THIEBAUX

• Making the Smart Grid Happen
• EternityII: Solving Edge Matching Puzzles

No Image Available

Research interests:

My research is focussed on Machine Learning. For details see my home page.

Bio:

I am the leader of the Machine Learning research group in NICTA.

Research interests:

My interests are in applied machine learning, in particular analysis of multimedia, social media, and spatial-temporal data. My recent projects include tracking real-world events in social media, event modeling for smarter cities, understanding pictures and words, large-scale image and video search and image and video tagging.

Research opportunities with Dr Lexing XIE

• Making Sense of Visual Folksonomy: a Flickr Study
• Multimedia Event Detection from Videos
• Tracking viral videos on Youtube
• Studying Real-world Events in Social Media
• Analysis of Spatial-temporal Data in Cities
• Computational Understanding of Paintings

Research interests:

Statistical Machine Learning, especially graphical models, kernel methods, semi-supervised learning, exponential families, Gaussian processes, Bregman divergence and differential geometry.

Research interests:

computer vision, inference and learning of graphic models

Duties:

Seminar Organizer of the Computer Vision & Robotics group

Research opportunities with Dr Yuhang ZHANG

• What, Where and How Many? Describing a Supermarket