- Be a female student enrolled in undergraduate or postgraduate study in the 2015 academic year.
- Be enrolled in a university in Asia Pacific, excluding Greater China* where we have an additional scholars’ retreat in China Mainland. Citizens, permanent residents, and international students are eligible to apply.
- Be majoring in computer science, computer engineering, or a closely related technical field.
- Exemplify leadership and demonstrate passion for increasing the involvement of women in computer science.
At the recent Genetic and Evolutionary Computation Conference, GECCO, Amsterdam, July 2013, they were awarded the best paper in the Genetics-based Machine Learning Track. GECCO is an Australian Research Council (ARC) A-rated conference. There were only 13 best papers awarded out of 570 submitted papers from the leading researchers worldwide.
The core idea of the work is to reuse already learnt information to solve increasingly harder problems, which the research team has shown to scale successfully to problems previously unsolved in machine learning. Surprisingly, nearly all other machine learning algorithms restart learning at the start of each new problem. This work introduces evolvable finite state machines into a problem's representation as a way of reusing cyclic building blocks, which are most appropriate for domains requiring repetitive patterns of knowledge. The work produced for the first time compact solutions that could solve any size problems in a number of important domains, such as parity problems. Evolutionary Computation is a branch of Artificial Intelligence which takes its inspiration from Darwinian ideas of survival of the fittest as multiple solutions are tested and bred with each other until the fittest survive. The research team form part of the Evolutionary Computation Research Group (ECRG), Victoria University of Wellington, which is one of the largest and most successful groups of this type in the world - currently with available doctoral places and scholarships available.
Track: Genetics Based Machine Learning
Extending Scalable Learning Classifier System with Cyclic Graphs to Solve Complex Large-Scale Boolean Problems. Muhammad Iqbal, Will N. Browne, Mengjie Zhang
(firstname.lastname@example.org; email@example.com; firstname.lastname@example.org)
Evolutionary computational techniques have had limited capabilities in solving large-scale problems, due to the large search space demanding large memory and much longer training time. Recently work has begun on automously reusing learnt building blocks of knowledge to scale from low dimensional problems to large-scale ones. An XCS-based classifier system has been shown to be scalable, through the addition of tree-like code fragments, to a limit beyond standard learning classifier systems. Self-modifying cartesian genetic programming (SMCGP) can provide general solutions to a number of problems, but the obtained solutions for large-scale problems are not easily interpretable. A limitation in both techniques is the lack of a cyclic representation, which is inherent in finite state machines. Hence this work introduces a state-machine based encoding scheme into scalable XCS, for the first time, in an attempt to develop a general scalable classifier system producing easily interpretable classifier rules. The proposed system has been tested on four different Boolean problem domains, i.e. even-parity, majority-on, carry, and multiplexer problems. The proposed approach outperformed standard XCS in three of the four problem domains. In addition, the evolved machines provide general solutions to the even-parity and carry problems that are easily interpretable as compared with the solutions obtained using SMCGP.
Victoria University is pleased to announce a co-funded PhD scholarship position (approx NZ$35k/year for 3 years) in Software Defined Networks (SDN). The position based at Victoria University will provide research which is of practical benefit to the SDN community and the NZ networking community in particular. This may be via applied research of use and interest to REANNZ, and possibly international research partners like ESnet.
Possible research areas
Interdomain SDN (“east-west interface”): how to connect SDN networks in different administrative domains, including BGP alternatives
Optimal network design: how to design and test through the use of automated software optimal SDN based network designs based on specified constraints (Eg, number of routes, redundancy of critical links, etc)
Migration to SDN: how to migrate common ISP/carrier architectures from non-SDN to SDN (including network management)
SDN network management: how to manage an SDN network without needing legacy protocol support (Eg, streaming statistics replacing use of SNMP polling)
Systems/networking software experience preferred
Algorithm development including its software implementation
Software development experience in C++/Java (python advantageous)
Software engineering/test practices such as unit testing
SDN/OpenFlow experience advantageous but not necessary
Networking protocols (Eg, BGP) advantageous but not necessary
Basic familiarity with network architectures and protocols, some exposure to new Future Internet Initiatives like OpenFlow, Named-Data Networking, GENI etc.
Strong ability to articulate technical problems and solutions, using various communication mechanisms such as presentations, conference papers etc.
Play it Again: Creating a Playable History of Australasian Digital Games, for Industry, Community and Research Purposes.
“So I've been looking at a passive way to measure the foetal heart rate. You can do this either by putting electrodes on the mother and then detecting the Electric Cardiogram (ECG) signal, or by listening with microphones, which is what my research has focused on. This is more like using the Pinard – the foetal stethoscope that midwives used before the invention of Doppler ultrasound, but much more reliable and easy to use.”Paul, who previously worked at Industrial Research Limited (IRL) in Gracefield, has been collaborating with his former colleagues to develop a method of using microphones to separate out the mixture of signals emitted from the womb by using a technique called Blind Source Separation.
“This isolates the foetal heart rate from the mother's heart rate, and the background noise. It's also a more passive method of monitoring that doesn't negatively impact upon either the mother or the baby.”Paul says he and his IRL counterparts are now working closely with Wellington midwives to collect data from mothers using this less invasive method.
“We've proved the method works in the last few weeks of pregnancy, but we're hopeful that eventually we will be able to use it from when a foetus is 18 weeks. Doppler ultrasound can work from about 12-14 weeks, but the important stages are later in the pregnancy.”
Daniel Akinyele has been awarded one of two student sponsorships to attend the 2014 NZ Wind Energy Conference and Exhibition, which will be held from the 14th-16th April at Te Papa Tongarewa in Wellington. In addition to presenting his proposal at the conference, Daniel will spend a day at Transpower, meeting staff and learning about the company, and about the electricity market and transmission planning and investment. Daniel’s proposal focuses on the intergration of wind power into distribution networks in New Zealand from the end-use and wider application perspectives. His research will model and simulate grid-connected micro and commercial-scale generation from residential and commercial premises respectively. It also considers microgrids connected to local grids for city-wide applications, which may also be disconnected from the network and operated independently in the event of a disaster. New Zealand probably has the most abundant wind energy resource in the world. Harnessing this natural resource for widespread distributed power generation (DPG) in New Zealand will not only provide support to the electrical network, improve the reliability and efficiency of the electricity supply and offer environmental benefits, but also aid the achievement of sustainable and future smart grid and help the government realize its goal of 90% renewable power by 2025. Daniel holds a National Diploma in Electrical and Electronic Engineering with Distinction from Osun State Polytechnic, Nigeria in 2002. He holds a First Class Degree in Electrical and Electronic Engineering from Nigeria’s Premier University, the University of Ibadan in 2008. He attended Loughborough University, UK for his Masters Degree in Renewable Energy Systems Technology, graduating with Distinction in 2010. He was a Senior Engineer in the renewable energy research group of the National Agency for Science and Engineering Infrastructure (NASENI) under the umbrella of the Federal Ministry of Science and Technology, Nigeria. He was responsible for renewable energy systems design and installation. He then joined the Department of Electrical and Information Engineering, Covenant University, Nigeria, as an assistant lecturer, teaching the fundamentals of Electrical Engineering and Network Analysis. He is currently a PhD student in the School of Engineering and Computer Science, Victoria University of Wellington, under the supervision of Dr Ramesh Rayudu.