ICIC2014 Keynote Speakers August
3-6, 2014 Taiyuan, China (http://www.ic-ic.org/2014/index.htm)
- Lewis Frank L
- Xin Yao
- Vincenzo Piuri
Reinforcement Learning Structures for
Real-Time Optimal Control and Differential Games
Lewis Frank L, National Academy of Inventors, Fellow
IEEE, InstMC, IFAC Moncrief-O'Donnell Endowed
Chair and Head, Advanced Controls & Sensors Group
UTA Research Institute (UTARI), The University of Texas
at Arlington, USA Personal website: http://www.uta.edu/utari/acs
Email: lewis@uta.edu
Abstract:
This talk will discuss some new adaptive control
structures for learning online the solutions to optimal
control problems and multi-player differential games.
Techniques from reinforcement learning are used to design
a new family of adaptive controllers based on
actor-critic mechanisms that converge in real time to
optimal control and game theoretic solutions.
Continuous-time systems are considered. Application of
reinforcement learning to continuous-time (CT) systems
has been hampered because the system Hamiltonian contains
the full system dynamics. Using our technique known as
Integral Reinforcement Learning (IRL), we will develop
reinforcement learning methods that do not require
knowledge of the system drift dynamics. In the linear
quadratic (LQ) case, the new RL adaptive control
algorithms learn the solution to the Riccati equation by
adaptation along the system motion trajectories. In the
case of nonlinear systems with general performance
measures, the algorithms learn the (approximate smooth
local) solutions of HJ or HJI equations. New algorithms
will be presented for solving online the non zero-sum
multi-player games for continuous-time systems. We use an
adaptive control structure motivated by reinforcement
learning policy iteration. Each player maintains two
adaptive learning structures, a critic network and an
actor network. The result is an adaptive control system
that learns based on the interplay of agents in a game,
to deliver true online gaming behavior. Bio-Sketch:
F.L. Lewis, Member, National Academy of Inventors. Fellow
IEEE, Fellow IFAC, Fellow U.K. Institute of Measurement &
Control, PE Texas, U.K. Chartered Engineer. UTA
Distinguished Scholar Professor, UTA Distinguished
Teaching Professor, and Moncrief-O'Donnell Chair at The
University of Texas at Arlington Research Institute. Qian
Ren Thousand Talents Professor, Northeastern University,
Shenyang, China. IEEE Control Systems Society
Distinguished Lecturer. He obtained the Bachelor's Degree
in Physics/EE and the MSEE at Rice University, the MS in
Aeronautical Engineering from Univ. W. Florida, and the
Ph.D. at Ga. Tech. He works in feedback control,
reinforcement learning, intelligent systems, and
distributed control systems. He is author of 6 U.S.
patents, 273 journal papers, 375 conference papers, 15
books, 44 chapters, and 11 journal special issues. He
received the Fulbright Research Award, NSF Research
Initiation Grant, ASEE Terman Award, Int. Neural Network
Soc. Gabor Award 2009, U.K. Inst Measurement & Control
Honeywell Field Engineering Medal 2009. Received IEEE
Computational Intelligence Society Neural Networks
Pioneer Award 2012. Distinguished Foreign Scholar,
Nanjing Univ. Science & Technology. Project 111 Professor
at Northeastern University, China. Received Outstanding
Service Award from Dallas IEEE Section, selected as
Engineer of the Year by Ft. Worth IEEE Section. Listed in
Ft. Worth Business Press Top 200 Leaders in
Manufacturing. Received the 2010 IEEE Region 5
Outstanding Engineering Educator Award and the 2010 UTA
Graduate Dean's Excellence in Doctoral Mentoring Award.
Elected to UTA Academy of Distinguished Teachers 2012.
Texas Regents Outstanding Teaching Award 2013. He served
on the NAE Committee on Space Station in 1995.
Recent Ensemble Algorithms for Online
and Class Imbalance Learning
Xin Yao, Professor & Ph D, Fellow IEEE, President IEEE
CIS Department of Computer Science, the
University of Birmingham, UK Personal website: http://www.cs.bham.ac.uk/~xin/
Email: X.Yao@cs.bham.ac.uk
Abstract:
Previous work on evolving neural networks has focused on
single neural networks. However, monolithic neural
networks have become too complex to train and evolve for
large and complex problems. It is often better to design
a collection of simpler neural networks that work
collectively and cooperatively to solve a large and
complex problem. The key issue here is how to design such
a collection, i.e., an ensemble, automatically so that it
has the best generalisation ability. This talk first
reviews briefly early work on evolving neural networks.
Then a previous idea of designing ensembles, negative
correlation learning, is explained. Lastly, several
recent studies are introduced, which analyze the impact
of diversity on online ensemble learning and that on
multi-class class imbalance learning. The ideas behind
some new ensemble algorithms for online learning, class
imbalance learning, and online class imbalance learning
will be presented. Applications of such new ensemble
learning algorithms will also be mentioned and future
research directions discussed. Bio-Sketch:
Xin Yao is a Chair (Professor) of Computer Science and
the Director of CERCIA (Centre of Excellence for Research
in Computational Intelligence and Applications) at the
University of Birmingham, UK. He is an IEEE Fellow and
the President (2014-15) of IEEE Computational
Intelligence Society (CIS). He won the 2001 IEEE Donald
G. Fink Prize Paper Award, 2010 IEEE Transactions on
Evolutionary Computation Outstanding Paper Award, 2010 BT
Gordon Radley Award for Best Author of Innovation
(Finalist), 2011 IEEE Transactions on Neural Networks
Outstanding Paper Award, and many other best paper
awards. He won the prestigious Royal Society Wolfson
Research Merit Award in 2012 and the IEEE CIS
Evolutionary Computation Pioneer Award in 2013. He was
the Editor-in-Chief (2003-08) of IEEE Transactions on
Evolutionary Computation and is an Associate Editor or
Editorial Member of more than ten other journals. He has
been invited to give 70+keynote/plenary speeches at
international conferences. His major research interests
include evolutionary computation and neural network
ensembles.
3D Surface Reconstruction by Using
Computational Intelligence Technologies
Vincenzo Piuri, Professor, Ph.D, IEEE Fellow
University degli Studi di Milano, Italy Personal
website: http://homes.di.unimi.it/piuri/
Email: vincenzo.piuri@unimi.it
Abstract:
Applications based on three-dimensional object models are
today very common, and can be found in many fields as
design, archeology, medicine, and entertainment. A
digital 3D model can be obtained, for example, by means
of physical object measurements performed by using a 3D
scanner. In this approach, an important step of the 3D
model building process consists of creating the object's
surface representation from a cloud of noisy points
sampled on the object itself. This process can be viewed
as the estimation of a function from a finite subset of
its points. Problems of this kind occur in many branches
of applied mathematics, and computer science. Many
techniques have been developed to face them, such as
interpolation, extrapolation, regression analysis, and
curve fitting. In computational intelligence this problem
is viewed as a supervised learning problem, where the
two-dimensional vector coordinates of the single point is
an input instance, while the third coordinate is
considered as an output label. The approximation function
identifies how to obtain labels from instances. Several
effective computational intelligence paradigms have been
developed for solving these kinds of problems. For the
solution of the function reconstruction problem, neural
techniques, generally, show a good trade-off between
computational complexity, accuracy and robustness of the
solution with respect to other methods. In this context,
there are many different paradigms which are able to find
the approximation function, e.g., Multi-layer Perceptron
Networks, Radial Basis Function (RBF) Networks, and
Support Vector Machines (SVM). In general, there is not a
single paradigm better than the others, but each one
performs differently depending on the application
context. This keynote speech is directed to introduce the
needs of the 3D surface reconstruction, to briefly
overview the techniques for surface reconstruction, to
analyze and discuss in detailed the neural techniques
suited for addressing this problem, and to present the
most recent results of research. Bio-Sketch:
Vincenzo PIURI has received his Ph.D. in computer
engineering at Politecnico di Milano, Italy (1989). He
has been Associate Professor at Politecnico di Milano,
Italy and Visiting Professor at the University of Texas
at Austin and at George Mason University, USA. He is Full
Professor in computer engineering (since 2000) and has
been Director of the Department of Information Technology
at the University degli Studi di Milano, Italy. His main
research interests are: signal and image processing,
machine learning, pattern analysis and recognition,
theory and industrial applications of neural networks,
intelligent measurement systems, industrial applications,
fault tolerance, cloud computing, internet-of-things,
digital processing architectures, embedded systems,
arithmetic architectures, and biometrics. Original
results have been published in more than 350 papers in
international journals, proceedings of international
conferences, books, and book chapters. He is Fellow of
the IEEE, Distinguished Scientist of ACM, and Senior
Member of INNS. He is Editor-in-Chief of the IEEE Systems
Journal (2013-15), and has been Associate Editor of the
IEEE Transactions on Neural Networks and the IEEE
Transactions on Instrumentation and Measurement. He has
been IEEE Director and IEEE Delegate for Division X,
President of the IEEE Computational Intelligence Society,
Vice President for Publications of the IEEE
Instrumentation and Measurement Society and the IEEE
Systems Council, Vice President for Membership of the
IEEE Computational Intelligence Society, and Vice
President for Education of the IEEE Biometrics Council.
He has been elected 2014 IEEE Vice President-elect for
Technical Activities. He received the IEEE
Instrumentation and Measurement Society Technical Award
(2002) for the contributions to the advancement of theory
and practice of computational intelligence in measurement
systems and industrial applications, the IEEE
Instrumentation and Measurement Society Distinguished
Service Award (2008), and the IEEE Computational
Intelligence Society Meritorious Service Award (2009).
|