|
Statistical Machine Learning Group
We develop techniques which can learn from data in a flexible and nonparametric fashion. This approach combines classical signal processing, statistics, pattern recognition, information theory, and artificial intelligence in a powerful way.
The Statistical Machine Learning Group is part of the
Computer Sciences Laboratory in
RSISE at the
ANU and part of
NICTA, Canberra, Australia.
Most members of the SML group are part of RSISE and NICTA.
An important component of an intelligent system is its ability to adapt to differing user needs and environments. The Statistical Machine Learning (SML) program researches methods of creating intelligent devices with the ability to learn. Ultimately, the aim is to build intelligent systems that adapt to user needs without needing a programmer to encode rules about how to act.
The systems researchers are constructing collect data from their environment, extract knowledge from data, and respond in an intelligent manner. The SML program focusses on research that can lead to products, processes and mechanisms that are increasingly usable; that hide sophisticated and complex processes behind simpler interfaces; that make use of information in vast databases; and that adapt to different environments and users.
For example, researchers are working to develop systems whereby devices are able to learn how to recognise a user's voice or handwriting. These devices should learn how their environment works by analysing and understanding large sets of data. They should also learn how to interact with their environment in order to reach the objectives they have been assigned.
The primary areas of interest to the program are
- kernel methods and statistics;
- rapid stochastic gradient methods;
- reinforcement learning and planning;
- information theory;
- bioinformatics.
See sml.nicta.com.au/ for a more detailed description.
We are always looking for good PhD candidates with
interest in Machine Learning.
Possible backgrounds are an honor's or master's degree in
physics, mathematics, computer sciences, or related field.
Application forms are available online from the Australian National University. Please have a look at the ANU and NICTA Education pages for further details. It is an advantage for applicants to contact potential supervisors before submitting the form. Any SML researcher may be considered as a potential supervisor for this purpose. Have a look at their projects for further details.
The PhD will be awarded by the
Australian National University, with NICTA
possibly paying a top-up scholarship.
The PhD program is 3-4 years.
Note that scholarships for non-residents of Australia are very
difficult to get, and you would typically need a couple of relevant
and high quality publications in the area already, or excellent results from a top university Masters degree.
Besides the official SML/NICTA projects, there are many other projects
in which SML is involved. A good way to find out
is to go to the list of people, and from there to the reseacher's homepages.
See sml.nicta.com.au/People
for an up to date and quite complete list of SML people and their research
interests.
|
