Home Plenary Speakers

Plenary Speakers:


Lazy Meta-Learning: Creating Customized Model Ensembles on Demand

Piero P. Bonissone

GE Global Research Center, Niskayuna, NY 12309, USA
This e-mail address is being protected from spambots. You need JavaScript enabled to view it

Abstract: In the not so distant future, we expect analytic models to become a commodity. We envision having access to a large number of data-driven models, obtained by a combination of crowdsourcing, crowd-servicing, outsourcing and legacy models. In this new context, the critical question will be model ensemble selection and fusion, rather than model generation. We try to address this issue by proposing customized model ensembles on demand, inspired by Lazy Learning. In our approach, referred to as Lazy Meta-Learning, for a given query we find the most relevant models from a model DB, using models meta-information. After retrieving the relevant models, we select a subset of models with highly uncorrelated errors. With these models we create an ensemble and use their meta-information for dynamic bias compensation and relevance weighting. The output is a weighted interpolation/extrapolation of the outputs of the models ensemble.  Furthermore, the confidence interval around the output is reduced as we increase the number of uncorrelated models in the ensemble. We have successfully tested this approach in an electric power management application.

Biography: A Chief Scientist at GE Global Research, Dr. Bonissone has been a pioneer in the field of fuzzy logic, AI, soft computing, and approximate reasoning systems applications since 1979. His current interests are the development of multi-criteria decision making systems for PHM and the automation of intelligent systems lifecycle to create, deploy, and maintain SC-based systems, providing customized performance while adapting to avoid obsolescence. 
He is a Fellow of the Institute of Electrical and Electronics Engineers (IEEE), of the Association for the Advancement of Artificial Intelligence (AAAI), of the International Fuzzy Systems Association (IFSA), and a Coolidge Fellow at GE Global Research.  He is the recipient of the 2012 Fuzzy Systems Pioneer Award from the IEEE Computational Intelligence Society. Since 2010, he is the President of the Scientific Committee of the European Centre of Soft Computing.  In 2008 he received the II Cajastur International Prize for Soft Computing from the European Centre of Soft Computing. In 2005 he received the Meritorious Service Award from the IEEE Computational Intelligence Society. He has received two Dushman Awards from GE Global Research. He served as Editor in Chief of the International Journal of Approximate Reasoning for 13 years. He is in the editorial board of five technical journals and is Editor-at-Large of the IEEE Computational Intelligence Magazine. He has co-edited six books and has over 150 publications in refereed journals, book chapters, and conference proceedings, with an H-Index of 27 (by Google Scholar). He received 61 patents issued from the US Patent Office (plus 50 pending patents).  From 1982 until 2005 he has been an Adjunct Professor at Rensselaer Polytechnic Institute, in Troy NY, where he has supervised 5 PhD theses and 33 Master theses. He has co-chaired 12 scientific conferences and symposia focused on Multi-Criteria Decision-Making, Fuzzy sets, Diagnostics, Prognostics, and Uncertainty Management in AI. Dr. Bonissone is very active in the IEEE, where is has been a member of the Fellow Evaluation Committee from 2007 to 2009. In 2002, while serving as President of the IEEE Neural Networks Society (now CIS) he was also a member of the IEEE Technical Board Activities (TAB). He has been an Executive Committee member of NNC/NNS/CIS society since 1993 and an IEEE CIS Distinguished Lecturer since 2004.

 Multiagent Learning Through Neuroevolution

Risto Miikkulainen

The University of Texas at Austin

Abstract: Neuroevolution is a promising approach for constructing intelligent agents in many complex tasks such as games, robotics, and decision making. It is also well suited for evolving team behavior for many multiagent tasks. However, new challenges and opportunities emerge in such tasks, including facilitating cooperation through reward sharing and communication, accelerating evolution through social learning, and measuring how good the resulting solutions are. In this talk I will review recent progress in these three areas, and suggest avenues for future work.

Biography: Risto Miikkulainen is a Professor of Computer Sciences at the University of Texas at Austin. He received an M.S. in Engineering from the Helsinki University of Technology, Finland, in 1986, and a Ph.D. in Computer Science from UCLA in 1990. His current research focuses on methods and applications of neuroevolution, as well as models of natural language processing, and self-organization of the visual cortex; he is an author of over 250 articles in these research areas. He is currently on the Board of Governors of the Neural Network Society, and an action editor of IEEE Transactions on Computational Intelligence and AI in Games and IEEE Transactions on Autonomous Mental Development.

 Reverse-Engineering the Human Auditory Pathway

Lloyd Watts

Abstract: By 2003, we had a good understanding of the characterization of sound which is carried out in the cochlea and auditory brainstem, and computer models capable of running these processes in isolation at near biological resolution in real-time.  By 2007, these advances had permitted the development of products in the area of two-microphone noise reduction for mobile phones, which led to viable business by 2010.
During 2003-2011, new fMRI, multi-electrode, and behavioral studies are illuminating the cortical brain regions responsible for separating sounds in mixtures, understanding speech in quiet and in noisy environments, producing speech, recognizing speakers, and understanding music.  During the same period, advances in computing and visualization hardware have permitted more advanced models of auditory brain processes to be simulated and displayed simultaneously, giving a rich perspective on the concurrent and interacting representations of sound and meaning which are developed and maintained in the brain.  While there is much still to be discovered and implemented in the next 15 years, we can show demonstrable progress on the scientifically ambitious and commercially important goal of reverse-engineering the human auditory pathway.

Biography: Lloyd Watts received the B.Sc. degree in Engineering Physics from Queen’s University in 1984, the M.A.Sc. degree in Electrical Engineering from Simon Fraser University in 1989, and the Ph.D. degree in Electrical Engineering from the California Institute of Technology in 1992, where he studied with Silicon Valley pioneer Carver Mead.
He has worked as an engineer at Microtel Pacific Research, Synaptics, and Interval Research Corporation.  In 2000, he founded Audience, Inc., to commercialize his research on reverse-engineering the human auditory pathway.  He served as Chairman and Chief Executive Officer from 2000-2005, raising $10M in venture capital financing and leading the development of the company’s core technologies.  In 2005, he transitioned to the role of Audience’s Chief Technology Officer, and in 2011 he became Chief Scientist.

 Unpacking and Understanding Evolutionary Algorithms

Xin Yao

Professor of computer science in the School of Computer Science at the University of Birmingham and the Director of the Centre of Excellence for Research in Computational Intelligence and Applications (CERCIA).

Abstract: Theoretical analysis of evolutionary algorithms (EAs) has made significant progresses in the last few years. There is an increased understanding of the computational time complexity of EAs on certain combinatorial optimisation problems. Complementary to the traditional time complexity analysis that focuses exclusively on the problem, e.g., the notion of NP-hardness, computational time complexity analysis of EAs emphasizes the relationship between algorithmic features and problem characteristics. The notion of EA-hardness tries to capture the essence of when and why a problem instance class is hard for what kind of EAs. Such an emphasis is motivated by the practical needs of insight and guidance for choosing different EAs for different problems. This talk first introduces some basic concepts in analysing EAs. Then the impact of different components of an EA will be studied in depth, including selection, mutation, crossover, parameter setting, and various interactions among them. Such theoretical analyses have revealed some interesting results, which might be counter-intuitive at the first sight. Finally, some future research directions of evolutionary computation will be discussed.

Biography: Xin Yao is a Professor (Chair) of Computer Science at the University of Birmingham, UK. He is an IEEE Fellow and a Distinguished Lecturer of IEEE Computational Intelligence Society. He won the 2001 IEEE Donald G. Fink Prize Paper Award, 2010 IEEE Transactions on Evolutionary Computation Outstanding Paper Award, 2011 IEEE Transactions on Neural Networks Outstanding Paper Award, and many other awards. He has more than 350 refereed publications in journals and conferences. In his spare time, he did the voluntary work as the Editor-in-Chief (2003-08) of IEEE Transactions on Evolutionary Computation, and is an associate editor or editorial board member of 12 international journals. He has been invited to give more than 60 keynote/plenary speeches at international conferences. His major research interests include evolutionary computation and neural network ensembles.





Contents by Vinh Quang Bui, DSARC, UNSW@ADFA, Australia / Template by Next Level Design