(listed in alphabetical order by last name)
Title: Latest Research Progress in Fireworks Algorithm and Its Applications
Speaker: Ying Tan
Abstract: Inspired from the collective behaviors of many swarm-based creatures in nature or social phenomena, swarm intelligence (SI) has been received attention and studied extensively, gradually becomes a class of efficiently intelligent optimization methods. Inspired by fireworks’ explosion in air, the so-called fireworks algorithm (FWA) was proposed in 2010. Since then, many improvements and beyond were proposed to increase the efficiency of FWA dramatically, furthermore, a variety of successful applications were reported to enrich the studies of FWA considerably. In this talk, the fireworks algorithm is briefly introduced and reviewed, then several effective improved fireworks algorithms are highlighted, individually. By changing the ways of calculating numbers and amplitudes of sparks in fireworks’ explosion, the improved FWA algorithms become more reasonable and explainable. In addition, the multi-objective fireworks algorithm and the graphic processing unit (GPU) based FWA are also briefly presented, particularly the GPU-based FWA is able to speed up the optimization process extremely. Extensive experiments on IEEE-CEC’s benchmark functions demonstrate that the improved fireworks algorithms significantly increase the accuracy of found solutions, yet decrease the running time sharply. Finally, several typical applications of FWA are concisely described while its future research directions are highlighted.
Short Bio: Ying Tan is a full professor and PhD advisor at Peking University, and director of Computational Intelligence Laboratory at Peking University. He was electee of CAS 100 Talents Program in 2005, worked at Chinese University of Hong Kong in 1999 and 2004-2005, and visited many universities including Columbia University, Kyushu University, Auckland University of Technology, etc. He is the inventor of Fireworks Algorithm (FWA). He serves as the Editor-in-Chief of International Journal of Computational Intelligence and Pattern Recognition (IJCIPR), the Associate Editor of IEEE Transactions on Evolutionary Computation (TEC), IEEE Transactions on Cybern
etics (CYB), IEEE Transactions on Neural Networks and Learning Systems (NNLS), International Journal of Swarm Intelligence Research (IJSIR), International Journal of Artificial Intelligence (IJAI), etc. He also served as an Editor of Springer’s Lecture Notes on Computer Science (LNCS) for 20+ volumes, and Guest Editors of several referred Journals, including IEEE/ACM Transactions on Computational Biology and Bioinformatics, Information Science, Neurocomputing, etc. He is a member of Emergent Technologies Technical Committee (ETTC) of IEEE Computational Intelligence Society since 2010. He is the founder and general chair of the ICSI International Conference series since 2010. He was also the general chair of joint general chair of 1st&2nd BRICS CCI, program committee co-chair of WCCI 2014, etc. He is the general chair of ICMEB’2017 at Seoul. He won the 2nd-Class Natural Science Award of China in 2009. His research interests include computational intelligence, swarm intelligence, swarm robotics, data mining, pattern recognition, intelligent information processing for information security and material engineering, etc. He has published more than 280 papers in refereed journals and conferences in these areas, and authored/co-authored 11 books and 12 chapters in book, and received 4 invention patents.
Title:Multi-objective evolutionary algorithms for solving complex optimization problems
Speaker: Xingyi Zhang
Abstract:Multi-objective evolutionary algorithms have been verified to be a useful technology for solving optimization problems during the last two decades, however, much work still deserves further investigations when addressing complex optimization tasks. In this talk, I will first briefly introduce the multi-objective evolutionary algorithms, and then mainly focus on three multi-objective evolutionary algorithms recently suggested by us to tackle complex optimization problems. The three works included in this presentation are: 1) a knee point driven evolutionary algorithm for many-objective optimization problems, 2) a decision variable clustering based evolutionary algorithm for large-scale optimization problems, and 3) a multi-objective evolutionary algorithm for task-oriented pattern mining task.
Short Bio:Xingyi Zhang is a full Professor and PhD advisor in School of Computer Science and Technology, Anhui University. He received the PhD degree from Huazhong University of Science and Technology in 2009 and visited University of Surrey, U.K. from 2013 to 2014. His main research interests include bio-inspired computing models and algorithms, multi-objective evolutionary algorithms and their applications, complex network analysis. He has published more than 40 papers, including more than 10 papers published in IEEE TEVC, IEEE TNNLS, IEEE TCYB and IEEE CIM. He has three ESI highly cited papers and one paper obtaining the IEEE TEVC outstanding paper award in 2018. He serves as a conference Chair of 2017 Data Driven Optimization of Complex Systems and Applications and 2015 Asian Conference on Membrane Computing, and also serves as an editorial broad member of Complex & Intelligent Systems and International Journal of Bio-Inspired Computation.
Title:Computational Complexity: a Membrane Computing Point of View
Speaker: Claudio Zandron
Abstract:Membrane systems are a parallel, nondeterministic, synchronous and distributed model of computation inspired by the structure and functioning of living cells. The model consists of a hierarchical structure composed by several membranes, embedded into a main membrane called the skin. Membranes divide the Euclidean space into regions, that contain multisets of objects and evolution rules.One interesting property of this model is the possibility to generate, mimicking the mitosis process, an exponential number of membranes in polynomial time, and use them in parallel to solve computationally hard problems. This possibility raises many interesting theoretical questions concerning the trade-off between time and space needed to solve various classes of computational problems by means of membrane systems.In this talk, I will illustrate the most important results concerning time and space complexity in the area of membrane computing, as well as the relations between classical complexity classes (defined in terms of Turing machines) and complexity classes defined in terms of membrane systems.
Short Bio:Claudio Zandron got the PhD in Computer Science from the University of Milan in 2002. Since 2006 he is Associate Professor at the Department of Informatics, Systems and Communication of the University of Milano-Bicocca, Italy.His research interests concern the areas of formal languages, molecular computing models, DNA computing, Membrane Computing and Computational Complexity. Co-author of about 100 research papers, presented at international conferences or published in international scientific journals, he won three times the best paper award at the International Conference on Membrane Computing.He partecipated in various Italian and European funded ICT projects.He is editor of the scientific journal Open Computer Science, and guest editor for various scientific volumes and journals (Theoretical Computer Science, Natural Computing).He is the chair of the steering committee of the International Conference on Membrane Computing, the conference chair in the executive board of the International Membrane Computing Society, anda member of the International Advisory Committee for “Energy, Materials, Nanotechnology (ENM) Meeting on Membranes”.
Title: The Recent Progress of Artificial Intelligence
Abstract:Since the concept of Turing machine has been first proposed in 1936, the capability of machines to perform intelligent tasks went on growing exponentially. Artificial Intelligence (AI), as an essential accelerator, pursues the target of making machines as intelligent as human beings. It has already reformed how we live, work, learning, discover and communicate. In this talk, I will review our recent progress on AI by introducing some representative advancements from algorithms to applications, and illustrate the stairs for its realization from perceiving to learning, reasoning and behaving. To push AI from the narrow to the general, many challenges lie ahead. I will bring some examples out into the open, and shed lights on our future target. Today, we teach machines how to be intelligent as ourselves. Tomorrow, they will be our partners to get into our daily life.
Short Bio:Dacheng Tao is Professor of Computer Science and ARC Future Fellow in
the School of Information Technologies and the Faculty of Engineering and Information Technologies at The University of Sydney. He was Professor of Computer Science and Director of the Centre for Artificial Intelligence in the University of Technology Sydney. He mainly applies statistics and mathematics to Artificial Intelligence and Data Science. His research interests spread across computer vision, data science, image processing, machine learning, and video surveillance. His research results have expounded in one monograph and 500+ publications at top journals and conferences, such as IEEE T-PAMI, T-NNLS, T-IP, JMLR, IJCV, IJCAI, AAAI, NIPS, ICML, CVPR, ICCV, ECCV, ICDM; and ACM SIGKDD, with several best paper awards, such as the best theory/algorithm paper runner up award in IEEE ICDM’07, the best student paper award in IEEE ICDM’13, and the 2014 ICDM 10-year highest-impact paper award. He received the 2015 Australian Scopus-Eureka Prize, the 2015 ACS Gold Disruptor Award and the 2015 UTS Vice-Chancellor’s Medal for Exceptional Research. He is a Fellow of the IEEE, OSA, IAPR and SPIE.
Title: Towards Compact Visual Analysis Systems
Abstract:In this talk, I will review several recent works in our group towards designing and implementing ting compact computer vision systems for retrieval, categorization, analysis, and inference of visual scenes. In particular, I will first review several works on compact binary code learning. Our main innovations lies in embedding the ordinal information into hash functions, a methodology among supervised and unsupervised learning, and can take merits of both. Second, I will review several recent works of our group in designing very compact and fast convolutional neural networks for visual analysis tasks. I will introduce our schemes on how to reduce the time cost of convolutional filters, as well as reducing the memory usage in fully-connected layers. I will also show our progress in FPGA based implementation of convolutional neural networks in various practical applications.
Short Bio: Rongrong Ji is currently a Mingjiang Chair Professor at the Department of Cognitive Science, School of Information Science and Engineering, Xiamen University. He is the founded director of Media Analytics and Computing Lab (Mac.xmu.edu.cn). Ji’s research falls in the field of computer vision, multimedia, and machine learning. His scholarly work mainly focuses on leveraging big data to build computer systems to understand visual scenes and human behaviors, inferring the semantics and retrieving instances for various emerging applications. My recent interests include compact visual descriptor, social media sentiment analysis, and holistic scene understanding. He has published 100+ papers in tier-1 journal and conferences like IJCV, TIP, CVPR, ICCV, ECCV, IJCAI, AAAI, ACM Multimedia etc, with over 4500 citations in the past 5 years.
In the past decade, Ji and his collaborators have developed some of the state-of-the-art mobile visual search systems and social multimedia analytics tools, with top performances in the MPEG Compact Descriptor for Visual Search (CDVS) standard evaluations. His work has also been recognized by ACM Multimedia 2011 Best Paper Award, Microsoft Fellowship 2007, and Best Thesis Award of Harbin Institute of Technology. His research has been supported by government agencies like National Science Foundation of China. He is the recipient of the National Science Foundation for Excellent Young Scholars (2014).
Title: Neuromorphic Cognitive Computing: A Learning and Memory Centered Approach
Abstract:Neuromorphic cognitive computing is a new theme of computing technology that aims for brain-like computing efficiency and intelligence. Neuromorphic computational models use neural spikes to represent the outputs of sensors and for communication between computing blocks, and using spike timing based learning algorithms. This talk will introduce the major concepts and developments in this interdisciplinary area from the learning and memory centered perspective, and discuss the major challenges and problems facing this field. This talk will focus on some recent research progresses, including spike based learning, sensory processing, and building robotic brain from neuroscience theories.
Short Bio:Huajin Tang received the B.Eng. degree from Zhejiang University, Hangzhou, China, M.Eng. degree from Shanghai Jiao Tong University, Shanghai, China, and Ph.D. degree from the National University of Singapore, Singapore, in 1998, 2001, and 2005, respectively. He was an R&D Engineer with STMicroelectronics, Singapore, from 2004 to 2006. From 2006 to 2008, he was a Postdoctoral Fellow with Queensland Brain Institute, University of Queensland, Australia. Since 2008 he was the Lab Head of Cognitive Computing and Robotic Cognitive at the Institute for Infocomm Research, A*STAR, Singapore. Currently he is National Youth-1000 Talent Distinguished Professor and Director of the Neuromorphic Computing Research Center, Sichuan University, China. His research interests include neuromorphic cognitive computing, neuromorphic hardware, and neuro-cognitive robotics. His work on Brain GPS was reported by MIT Technology Review on 2015. He received IEEE Outstanding TNNLS Paper Award 2016. He is an Associate Editor for IEEE Trans. On Neural Networks and Learning Systems, IEEE Trans. on Cognitive and Developmental Systems, and Frontiers in Neuromorphic Engineering.