Click here for the latest conference
> SUBMISSION DEADLINE
July 26, 2015 August 19, 2015 (firm deadline)
> AUTHOR NOTIFICATION
September 06, 2015 --> September 30, 2015
> CAMERA-READY SUBMISSION
September 27, 2015 October 20, 2015
> REGISTRATION DEADLINE
October 10, 2015 --> October 20, 2015
> CONFERENCE DATES
Keynote Talks for SOICT
School of Computer Engineering
Nanyang Technological University
Title: Towards Evolutionary Multitasking: A New Paradigm in Evolutionary Computation
The design of population-based search algorithms of evolutionary computation (EC) has traditionally been focused on efficiently solving a single optimization task at a time. It is only very recently that a new paradigm in EC, namely, multifactorial optimization (MFO), has been introduced to explore the potential of evolutionary multitasking (Gupta, Ong, & Feng, 2015). The nomenclature signifies a multitasking search involving multiple optimization tasks at once, with each task contributing a unique factor influencing the evolution of a single population of individuals. MFO is found to leverage the scope for implicit genetic transfer offered by the population in a simple and elegant manner, thereby opening doors to a plethora of new research opportunities in EC, dealing, in particular, with the exploitation of underlying synergies between seemingly unrelated tasks. A strong practical motivation for the paradigm is derived from the rapidly expanding popularity of cloud computing (CC) services. It is noted that CC characteristically provides an environment in which multiple jobs can be received from multiple users at the same time. Thus, assuming each job to correspond to some kind of optimization task, as may be the case in a cloud-based on-demand optimization service, the CC environment is expected to lend itself nicely to the unique features of MFO.
In this talk, the formalization of the concept of MFO is first introduced. A fitness landscape-based approach towards understanding what is truly meant by there being underlying synergies (or what we term as genetic complementarities) between optimization tasks is then discussed. Accordingly, a synergy metric capable of quantifying the complementarity, which shall later be shown to act as a "qualitative" predictor of the success of multitasking is also presented (Gupta, Ong, Da, Feng, and Handoko, 2015). With the above in mind, a novel evolutionary algorithm (EA) for MFO is proposed, one that is inspired by bio-cultural models of multifactorial inheritance, so as to best harness the genetic complementarity between tasks. The salient feature of the algorithm is that it incorporates a unified solution representation scheme which, to a large extent, unites the fields of continuous and discrete optimization. The efficacy of the proposed algorithm, and the concept of MFO in general, shall finally be substantiated via a variety of computation experiments in intra and inter-domain evolutionary multitasking.
Yew-Soon Ong is a Professor and Director of the A*Star SIMTECH-NTU Joint Lab on Complex Systems at the Nanyang Technological University, Singapore, and the Programme Principal Investigator of the Rolls-Royce@NTU Corporate Lab. He received his PhD degree on Artificial Intelligence in complex design from the Computational Engineering and Design Center, University of Southampton, United Kingdom in 2003. His current research interest in computational intelligence spans across memetic computation, evolutionary computation, machine learning, Big Data Analytics and agent-based systems.
He is the founding Technical Editor-in-Chief of Memetic Computing Journal, founding Chief Editor of the Springer book series on studies in adaptation, learning, and optimization, Associate Editor of the IEEE Transactions on Evolutionary Computation, the IEEE Transactions on Neural Networks & Learning Systems, IEEE Computational Intelligence Magazine, IEEE Transactions on Cybernetics, IEEE Transactions on Big Data, Soft Computing, International Journal of System Sciences and others. He has coauthored over 200 refereed publications and his research grants in the last five years amounts to a total of more than 25 million Singapore dollars. His research work on Memetic Algorithm was featured by Thomson Scientific's Essential Science Indicators as one of the most cited emerging area of research in August 2007. And he is recipient of the 2015 IEEE Computational Intelligence Magazine Outstanding Paper Award and the 2012 IEEE Transactions on Evolutionary Computation Outstanding Paper Award for his work pertaining to Memetic Computation. Several of his research technologies in memetic computation have been commercialized and licensed to companies and institutions worldwide. Over the last 5 years, he has been invited to deliver over 20 keynote, plenary or lecture speeches at international conferences, workshops and lecture series.
He chaired the IEEE Computational Intelligence Society Emerging Technologies Technical Committee from 2012-2013 and the IEEE Computational Intelligence Society Intelligent Systems and Applications Technical Committee from 2013-2014. Presently, he is Conference Chair of the Congress on Evolutionary Computation, World Congress on Computational Intelligence, Vancouver, Canada, 2016 and also secretary of the IEEE Transactions on Computational Intelligence and AI in Games steering committee. Homepage: http://rxsupersales.shop/
National Institute of Informatics and the Graduate
University for Advanced Studies (SOKENDAI), Tokyo, Japan
Title: Singularity of Future Computer-System Networks
As a supercomputer becomes large, over million cores using over million Watts, its network design is more complex.
In this talk, I explain its network requirements and trends, especially network topology for low communication latency, and low power consumption.
I then recommend two key unique technologies, random network topologies and free-space optics for making future supercomputers and datacenters.
Michihiro Koibuchi received the PhD degrees from Keio University, Yokohama, Kanagawa, Japan, in 2003. He is currently an Associate Professor at National Institute of Informatics, and the Graduate University for Advanced Studies (SOKENDAI), Tokyo, Japan.
His research interests include the areas of high-performance computing and interconnection networks.
He published over 100 conference and journal papers (6 in IEEE Trans. on Parallel and Distributed Systems and 2 in IEEE Trans. on Computers), and has served as conference program committees (IEEE Cluster, CCGrid, ICPP, ICPADS and ASP-DAC). He has proposed and investigated the use of random network topologies and the free-space optics for high-performance computing systems.
KU Leuven , Belgium
Title: The Future of Programming is Functional
More and more mainstream programming languages are adopting concepts from
Functional Programming. Good examples are the recent support for lambda
expressions, streams and the Optional type in Java 8, the lambda functions
in C++13 and the LINQ framework in C#.
This talk traces these features back to their source in the Functional
Programming paradigm and considers what Functional Programming has in store for
the future of mainstream programming. In particular we consider the explicit
and flexible control of side-effects in the form of monads (aka the
overloadable semi-colon). Monads now come in a new and more palatable form:
(algebraic) effect handlers. Effect handlers generalise the well-known
exception handlers to support a wide-range of user-defined side-effects that
can be easily combined.
Tom Schrijvers obtained his Ph.D. in computer science at KU Leuven (Belgium) with congratulations of the jury. He was associate professor at Ghent University (Belgium) before taking up the position of senior research professor at KU Leuven. Currently he heads the programming languages team within the Declarative Languages & Artificial Intelligence group of the KU Leuven Department of Computer Science. His team covers a broad range of topics in the area of programming languages, with a particular focus on declarative languages (functional, logic and constraint programming) and programming language theory.
Copyright © 2015 SoICT; Contact webmaster
The website is optimized for Mozilla Firefox with a screen resolution of 1024x768