Projects

Project title:

Behaviour in Autonomous Multi-agent Systems

Chief Investigators: Dr Stephan Chalup, Dr Michael Quinlan, Dr Oliver Obst, Dr Stephen R. Young
Publications:
  1. Quinlan Michael Joseph, Obst Oliver, Chalup Stephan, ’Towards autonomous strategy decisions in the RoboCup Four-Legged League’, 7th IJCAI International Workshop on Nonmontonic Reasoning, Action and Change. Proceedings, Hyderabad, India (2007)
  2. Quinlan Michael Joseph, Chalup Stephan, ’Impact of Tactical Variations in the RoboCup Four-Legged League’, Proceedings of International Symposium on Practical Cognitive Agents and Robots, Perth, WA, Australia (2006)
  3. Young Stephen Robert, Chalup Stephan, ’Towards Robot Soccer Team Behaviours Through Approximate Simulation’, Proceedings of 4th IEEE International Conference on Development and Learning, INTEX Osaka, Japan (2005)

Project title:

Dynamic Language Processing

Chief Investigators: Dr Stephan Chalup
Dr Alan Blair
Publications:
  1. Stephan Chalup and Alan D. Blair (1999). "Hill climbing in recurrent neural networks for learning the an bn cn language". In: ICONIP'99, 6th International Conference on Neural Information Processing, Proceedings. Perth, Western Australia, 16-20 November 1999, Volume 2. pp. 508–513, ISBN: 0-7803-5871-6, IEEE.(PDF-151KB)
  2. Stephan K. Chalup and Alan D. Blair (2002), “Software for Analysing Recurrent Neural Nets that Learn to Predict Non-Regular Languages”, In: Pieter W. Adriaans and Henning Fernau and Menno van Zaanen, “Grammatical Inference: Algorithms and Applications, 6th International Colloquium: ICGI 2002, Amsterdam, The Netherlands, September 23-25, 2002, Proceedings”. Lecture Notes in Computer Science LNCS 2484, pp.296—298, ISBN 3-540-44239-1, Springer-Verlag.(PDF-95KB).
  3. Stephan K. Chalup and Alan D. Blair (2003). Incremental Training of First Order Recurrent Neural Networks to Predict a Context-Sensitive Language. Neural Networks 16(7), pp. 955-972. (PDF-402KB)
  4. Stephan K. Chalup and Alan D. Blair (2003). Incremental Learning for RNNs: How Does It Affect Performance and Hidden Unit Activation? RNNaissance Workshop–NIPS 2003.(abstract, unpublished)(PDF-35KB)

 

Back to top…
Project title: Kernel Methods in Finance and Complexity Management

Chief Investigators:

Dr Stephan Chalup
Professor Detlef Seese

Postgraduates: Mr Tobias Dietrich
Mr Andreas Mitschele
Mr Christian Ullrich
Publications:
  1. Andreas Mitschele, Detlef Seese, Frank Schlottmann, and Stephan Chalup. Applications of Kernel Methods in Financial Risk Management. 12th International Conference on ”Computing in Economics and Finance” Amathus Beach Hotel, Limassol, Cyprus, 22-24 June, 2006.
  2. Christian Max Ullrich, Detlef Seese, Stephan Chalup. Foreign Exchange Trading with Support Vector Machines.  In Proceedings of the 30th Annual Conference of the German Classification Society (GfKI 2006), pp. 1-9. 2006.
  3. Tobias Dietrich, Detlef Seese, and Stephan K. Chalup. Classification of e-bay bidding
    characteristics. IADIS International Journal on WWW/Internet 4(1), pp. 111–125, ISSN: 1645–7641, 2006.
  4. Christian Ullrich, Detlef Seese, and Stephan Chalup. Predicting Foreign Exchange Rate Return Directions with Support Vector Machines. Proceedings of the 4th Australasian Data Mining Conference (AusDM05), Simeon J. Simoff, Graham J. Williams, John Galloway and Inna Kolyshkina (editors), December, 2005, Sydney, Australia, pp. 221-240.
  5. Tobias Dietrich, Detlef Seese, and Stephan Chalup. Differences in Bidding Characteristics on ebay.de. Proceedings of the IADIS International Conference e-Commerce 2005 Porto, Portugal December 15-17, 2005, Nitya Karmakar and Pedro Isaias (editors), ISBN: 972-8924-06-2, pp. 3–10, IADIS Press, 2005.
  6. Stephan Chalup and Andreas Mitschele. Kernel Methods in Finance. Chapter 27, pp. 655-687; In: Detlef Seese, Christof Weinhardt and Frank Schlottmann (Eds.). Handbook on Information Technology in Finance; Series: International Handbooks on Information Systems; ISBN: 978-3-540-49486-7; Springer-Verlag Berlin Heidelberg, 2008.

Project title: Machine Learning on AIBO Robots
Postgraduate: Mr Michael Quinlan (completed 2006)
Supervisors: Dr Stephan Chalup
Professor Rick Middleton
Publications:
  1. Stephan K. Chalup, Craig L. Murch, and Michael J. Quinlan. Machine Learning with AIBO Robots in the Four Legged League of RoboCup. IEEE Transactions on Systems, Man, and Cybernetics—Part C, Vol. 37, No. 3, pp. 297-310, May 2007. (PDF-810KB )
  2. Michael J. Quinlan and Stephan K. Chalup and Richard H. Middleton. Application of SVMs for Colour Classification and Collision Detection with AIBO Robots. Advances in Neural Information Processing Systems 16, (NIPS’2003), Cambridge, MA, MIT Press, 2004. (PDF, 262KB )
  3. M. J. Quinlan, S. K. Chalup, R. H. Middleton. Techniques for Improving Vision and Locomotion on the Sony AIBO Robot. In: Jonathan Roberts and Gordon Wyeth (eds.), Proceedings of the 2003 Australasian Conference on Robotics & Automation (ACRA’2003).
  4. . M. J. Quinlan, C. Murch, R. H. Middleton, S. K. Chalup. Traction Monitoring for Collision Detection with Legged Robots. Lecture Notes in Artificial Intelligence LNAI 3020, pp. 374–384, 2004. [Engineering Challenge Paper Award, RoboCup 2003]

Project title: Recognition and Modelling of Faces in Human–Robot Communication and Interaction
Postgraduate: Mr Kenny Hong
Supervisors: Dr Stephan Chalup
Dr Suhuai Luo

 

Back to top…
Project title: Shaping social and cultural spaces: the application of computer visualisation and machine learning techniques to the design of architectural and urban spaces.
Chief Investigators: Professor Michael Ostwald
Dr Stephan Chalup
Support: ARC Large Grant 2007-2009
Publications:
  1. Stephan K. Chalup, Riley Clement, Michael J. Ostwald and Chris Tucker
    Applications of Manifold Learning in Architectural Facade and Streetscape Analysis, Workshop on Novel Applications of Dimensionality Reduction at NIPS 2006.
  2. Stephan K. Chalup, Riley Clement, Joshua Marshall, Chris Tucker, and Michael J. Ostwald. Representations of Streetscape Perceptions Through Manifold Learning in the Space of Hough Arrays. 2007 IEEE Symposium on Artificial Life, April 1-5, 2007. (PDF, 2.14MB)
  3. Stephan K. Chalup, Riley Clement, Chris Tucker and Michael J. Ostwald. Modelling Architectural Visual Experience Using Non-linear Dimensionality Reduction. In: M. Randall, H. Abbass, and J. Wiles (Eds.): ACAL 2007, LNAI 4828, pp. 84-95, 2007.
  4. Tucker Christopher Charles, Ostwald Michael, Marshall Joshua Phillip, Chalup Stephan, ’The visual qualities of liveable streets’, Towards Solutions for a Liveable Future: Progress, Practice, Performance, People. Proceedings of the 41st Annual Conference of the Architectural Science Association, Melbourne (2007)
  5. S. K. Chalup, N. Henderson, M. J. Ostwald, and L. Wiklendt. A method for cityscape analysis by determining the fractal dimension of its skyline. In: 42nd Annual Conference of the Australian and New Zealand Architectural Science Association (ANSAScA 2008) November 2008, Newcastle, Australia, 2008. forthcoming.
    M. J. Ostwald, J. Vaughan, and S. Chalup. A computational analysis of fractal dimensions in the architecture of Eileen Gray. In ACADIA 2008, Silicon + Skin: Biological Processes and Computation, October 16 - 19, 2008.
  6. Stephan K. Chalup, Kenny Hong and Michael J. Ostwald. A Face-House Paradigm for Architectural Scene Analysis. In: International Conference on Soft Computing as Transdisciplinary Science and Technology (CSTST 2008), 2008.

Project title: Sound-scape Visualisation through Dimensionality Reduction
Chief Investigators: Dr Stephan Chalup and Dr. Kaushik Mahata
Postgraduate: Mr Aaron Wong
Publications:
  1. Aaron Wong and Stephan K. Chalup. Towards Visualisation of Sound-scapes Through Dimensionality Reduction, 2008 IEEE World Congress on Computational Intelligence (WCCI), Hong Kong, June 1-6, 2008

Project title: Spiking Neural Networks for Motor Control
Chief Investigators: Dr Stephan Chalup
Dr Maria Seron
Postgraduate: Mr Lukasz Wiklendt
Support: The University of Newcastle, CDSC
Research Areas :
  •  Acrobot swing-up and stabilisation
  •  Employ spiking neural networks in a computer simulation study
  •  Use evolutionary computation for training
  •  Bi-ped simulation study
Publications:
  1. Lukasz Wiklendt, Stephan K. Chalup and Maria Seron. Quadratic Leaky Integrate-and-Fire Neural Network Tuned with an Evolution Strategy for a Simulated 3D Biped Walking Controller, 8th International Conference on Hybrid Intelligent Systems (HIS 2008), IEEE Computer Society Press 2008 (forthcoming).
  2. Chalup Stephan, Middleton Richard Hume, Quinlan Michael Joseph, Wiklendt Lukasz Sebastian, ’Neurocomputational aspects of legged locomotion motor control’, Proceedings of the Australian Neuroscience Society, 15 105 (2004).

Project title: The Machine Intelligence Hex Project
Chief Investigators: Dr Stephan Chalup
Research Assistant: Mr Drew Mellor
Collaborator: Dr Frances Rosamond
Support: Discipline of CSSE
Publications:
  1. Stephan K. Chalup, Drew Mellor, and Fran Rosamond. The Machine Intelligence Hex Project. Computer Science Education 15(4), pp. 245–273, Routledge, December 2005.  

 

Back to top…