Thursday 21 September 2017

Educational Activities

Education Multimedia Subcommittee

The CIS Education Multimedia Subcommittee intend to build up a reference centre of links to good quality short interactive multimedia demonstrations or short videos on CI. These can be suitable for a range of audiences, and can link to externally hosted resources. We invite you to submit recommendations for resources you have come across that would benefit the wider CIS community. please email suggestions to Annabel Latham (a.latham@mmu.ac.uk).

IEEE CIS Webinar on "The Magic of Monte Carlo Tree Search", 4pm (BST), Friday, Sept. 29 2017


Speaker
Dr. Mark Winands, Associate Professor, Department of Data Science & Knowledge Engineering, Maastricht University. 

Abstract
Monte-Carlo Tree Search (MCTS) has caused a revolution in computer game-playing the last few years. The most well-known example is the game of Go. MCTS is a best-first search technique that gradually builds up a search tree, guided by  Monte-Carlo  simulations. In contrast to many classic search techniques, MCTS does not require a heuristic evaluation function that assesses the current board position. In this talk I will discuss its background, basic mechanism, and standard enhancements that have improved the technique considerably. Successful applications of the technique in several domains will be mentioned.

Bio
Mark Winands received a Ph.D. degree in Artificial Intelligence from the Department of Computer Science, Maastricht University, Maastricht, The Netherlands, in 2004. Currently, he is an Associate Professor at the Department of Data Science & Knowledge Engineering, Maastricht University. His research interests include heuristic search, machine learning and games. He has written more than eighty scientific publications on Games & AI. Mark serves as an editor-in-chief of the ICGA Journal, associate editor of IEEE Transactions on Computational Intelligence and AI in Games, editor of Game & Puzzle Design. He is a member of the Games Technical Committee (GTC) | IEEE Computational Intelligence Society, and member of working group 14.4 – Entertainment Games | IFIP TC14 on Entertainment Computing.


Please register for The Magic of Monte Carlo Tree Search - Sep 29, 2017 on 4:00 PM BST at: 
https://attendee.gotowebinar.com/register/5997375619679435011

Friday 15 September 2017

IEEE Transactions on Neural Networks and Learning Systems; Volume 28, Issue 9, September 2017

The following articles appeared in the latest issue of IEEE Transactions on Neural Networks and Learning Systems: Volume 28, Issue 9, September 2017.

This issue published papers on feature selection, self-organized neural network, manifold learning, gradient descent, support vector machines, adaptive dynamic programming, neuroadaptive control, recurrent neural network, among others. We welcome your submissions to IEEE TNNLS.

These articles can be retrieved on IEEE Xplore:
http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=5962385
or directly by clicking the individual paper URL below.

IEEE Transactions on Neural Networks and Learning Systems;
Volume 28, Issue 9, September 2017.


1. Semisupervised Feature Selection Based on Relevance and Redundancy Criteria
Author(s): Jin Xu; Bo Tang; Haibo He; Hong Man
Page(s): 1974 - 1984
http://ieeexplore.ieee.org/document/7475902/

2. Visual Recognition by Learning From Web Data via Weakly Supervised Domain Generalization
Author(s): Li Niu; Wen Li; Dong Xu; Jianfei Cai
Page(s): 1985 - 1999
http://ieeexplore.ieee.org/document/7482802/

3. The Growing Hierarchical Neural Gas Self-Organizing Neural Network
Author(s): Esteban J. Palomo; Ezequiel López-Rubio
Page(s): 2000 - 2009
http://ieeexplore.ieee.org/document/7484280/

4. A Novel Locally Linear KNN Method With Applications to Visual Recognition
Author(s): Qingfeng Liu; Chengjun Liu
Page(s): 2010 - 2021
http://ieeexplore.ieee.org/document/7486998/

5. An Approach to Stable Gradient-Descent Adaptation of Higher Order Neural Units
Author(s): Ivo Bukovsky; Noriyasu Homma
Page(s): 2022 - 2034
http://ieeexplore.ieee.org/document/7487017/

6. Descriptor Learning via Supervised Manifold Regularization for Multioutput Regression
Author(s): Xiantong Zhen; Mengyang Yu; Ali Islam; Mousumi Bhaduri; Ian Chan; Shuo Li
Page(s): 2035 - 2047
http://ieeexplore.ieee.org/document/7487053/

7. Online Learning of Hierarchical Pitman–Yor Process Mixture of Generalized Dirichlet Distributions With Feature Selection
Author(s): Wentao Fan; Hassen Sallay; Nizar Bouguila
Page(s): 2048 - 2061
http://ieeexplore.ieee.org/document/7488264/

8. A Novel Neural Network for Generally Constrained Variational Inequalities
Author(s): Xingbao Gao; Li-Zhi Liao
Page(s): 2062 - 2075
http://ieeexplore.ieee.org/document/7490354/

9. Budget Online Learning Algorithm for Least Squares SVM
Author(s): Ling Jian; Shuqian Shen; Jundong Li; Xijun Liang; Lei Li
Page(s): 2076 - 2087
http://ieeexplore.ieee.org/document/7490353/

10. Integral Sliding Mode Fault-Tolerant Control for Uncertain Linear Systems Over Networks With Signals Quantization
Author(s): Li-Ying Hao; Ju H. Park; Dan Ye
Page(s): 2088 - 2100
http://ieeexplore.ieee.org/document/7490337/

11. Neural Network-Based Passive Filtering for Delayed Neutral-Type Semi-Markovian Jump Systems
Author(s): Peng Shi; Fanbiao Li; Ligang Wu; Cheng-Chew Lim
Page(s): 2101 - 2114
http://ieeexplore.ieee.org/document/7491305/

12. Online Regression for Data With Changepoints Using Gaussian Processes and Reusable Models
Author(s): Robert C. Grande; Thomas J. Walsh; Girish Chowdhary; Sarah Ferguson; Jonathan P. How
Page(s): 2115 - 2128
http://ieeexplore.ieee.org/document/7491276/

13. Large-Cone Nonnegative Matrix Factorization
Author(s): Tongliang Liu; Mingming Gong; Dacheng Tao
Page(s): 2129 - 2142
http://ieeexplore.ieee.org/document/7492255/

14. Containment Control for Second-Order Multiagent Systems Communicating Over Heterogeneous Networks
Author(s): Jiahu Qin; Wei Xing Zheng; Huijun Gao; Qichao Ma; Weiming Fu
Page(s): 2143 - 2155
http://ieeexplore.ieee.org/document/7494594/

15. Predictor-Based Neural Dynamic Surface Control for Uncertain Nonlinear Systems in Strict-Feedback Form
Author(s): Zhouhua Peng; Dan Wang; Jun Wang
Page(s): 2156 - 2167
http://ieeexplore.ieee.org/document/7497592/

16. Robust Image Regression Based on the Extended Matrix Variate Power Exponential Distribution of Dependent Noise
Author(s): Lei Luo; Jian Yang; Jianjun Qian; Ying Tai; Gui-Fu Lu
Page(s): 2168 - 2182
http://ieeexplore.ieee.org/document/7498630/

17. Smooth Neuroadaptive PI Tracking Control of Nonlinear Systems With Unknown and Nonsmooth Actuation Characteristics
Author(s): Yongduan Song; Junxia Guo; Xiucai Huang
Page(s): 2183 - 2195
http://ieeexplore.ieee.org/document/7498644/

18. Methodology of Recurrent Laguerre–Volterra Network for Modeling Nonlinear Dynamic Systems
Author(s): Kunling Geng; Vasilis Z. Marmarelis
Page(s): 2196 - 2208
http://ieeexplore.ieee.org/document/7499832/

19. Dynamic Surface Control for a Class of Nonlinear Feedback Linearizable Systems With Actuator Failures
Author(s): Kendrick Amezquita Semprun; Lin Yan; Waseem Aslam Butt; Peter C. Y. Chen
Page(s): 2209 - 2214
http://ieeexplore.ieee.org/document/7485822/

20. A New Powered Lower Limb Prosthesis Control Framework Based on Adaptive Dynamic Programming
Author(s): Yue Wen; Jennie Si; Xiang Gao; Stephanie Huang; He Helen Huang
Page(s): 2215 - 2220
http://ieeexplore.ieee.org/document/7508991/

CFP: IEEE TETCI Special Issue on Computational Intelligence in Data-Driven Optimization (Jan 31, 2018)

I. AIM AND SCOPE

Most evolutionary algorithms and other meta-heuristic search methods typically assume that there are explicit objective functions available for fitness evaluations. In the real world, however, such explicit objective functions may not exist in many cases. For example, in many process industry optimization problems, no explicit models exist for describing the relationship between the final quality of the product and the decision variables, such as control loop outputs and grinding particle size in hematite grinding processes. Therefore, some computationally very intensive numerical simulation, such as computational fluid dynamic simulations or finite element analysis or even physical experiments, are instead conducted as the way to evaluate the fitness value. Thus, historical experimental data becomes significantly important and can be used for optimization. There are also cases where only factual data can be collected.

For solving such optimization problems, evolutionary optimization can be conducted only using a data-driven approach. Data-driven evolutionary optimization can largely be divided into two paradigms, one termed off-line data-driven optimization, where no additional data can be sampled during optimization, and the other is called on-line data-driven optimization, where only a limited number of new data points can be actively sampled during optimization. For both paradigms of data-driven optimization, seamless integration of machine learning techniques, such as model selection, ensemble learning, active learning, semi-supervised learning and transfer learning with evolutionary optimization are essential, due to the fact that data acquisition is very expensive, either computationally or costly.

This special issue aims to present the most recent advances in data-driven optimization, in particular in the integration of evolutionary algorithms and other meta-heuristic search methods with machine learning techniques, neural networks and fuzzy logic systems for surrogate modelling, data mining, preference articulation, and decision-making.

II. TOPICS

The topics of this special issue include but are not limited to the following topics:

• Surrogate-assisted optimization of computationally expensive problems
• Adaptive sampling using active learning and statistical learning techniques
• Surrogate model management in single and multiobjective optimization
• Semi-supervised and transfer learning in data driven optimization
• Machine learning for distributed data driven optimization
• Knowledge mining and transfer for data-driven optimization
• Data-driven large scale and/or many-objective optimization problems
• Preference modeling and articulation in multi- and manyobjective optimization
• Real world applications including multidisciplinary optimization

III. IMPORTANT DATES

• Paper submission deadline: January 31, 2018
• Notice of the first round review: April 15, 2018
• Revision due: June 15, 2018
• Final notice of acceptance/reject: July 30, 2018

IV. SUBMISSION

Manuscripts should be prepared according to the “Information for Authors” section of the journal (http://cis.ieee.org/ieee-transactions-on-emerging-topics-incomputational-intelligence.html) and submissions should be done through the journal submission website: https://mc.manuscriptcentral.com/tetci-ieee, by selecting the Manuscript Type of “Computational Intelligence in DataDriven Optimization” and clearly marking “Computational Intelligence in Data-Driven Optimization Special Issue Paper” as comments to the Editor-in-Chief. Submitted papers will be reviewed by at least three different expert reviewers. Submission of a manuscript implies that it is the authors original unpublished work and is not being submitted for possible publication elsewhere.

V. GUEST EDITORS

Dr. Chaoli Sun, Department of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan, Shanxi 030024 China. Email: chaoli.sun.cn@gmail.com

Dr. Handing Wang, Department of Computer Science, University of Surrey, Guildford, GU2 7XH, UK. Email: handing.wang@surrey.ac.uk

Prof. Wenli Du, School of Information Science & Engineering, East China University of Science and Technology, Shanghai, 200237, China. Email: wldu@ecust.edu.cn

Prof. Yaochu Jin, Department of Computer Science, University of Surrey, Guildford, GU2 7XH, UK. Email: yaochu.jin@surrey.ac.uk

CFP: IEEE CIM Special Issue on Computational Intelligence in Finance and Economics (Dec 31)

Aims and Scope
Real-world problems in the financial domain often involve complexity, noise, uncertainty and vagueness. It is difficult to handle such problems by the conventional analytical and numerical paradigms in addition to the need to handle large volumes of data at a proper speed.

Over the last decades, Computational Intelligence (CI) has been gaining traction in the domain as both a problem-solving strategy and a new analysis tool. Conventional methodologies in financial engineering, predictive analytics and business analytics have various limitations and usually need significant user/expert engagement in modelling and application. CI has established a new research track as well as a new stream of methodologies to be used in financial and economic analysis. Capacity of CI is much higher than traditional approaches such as econometrics and time series analysis. CI can handle not only expert knowledge but also knowledge extracted automatically from data with by utilizing sophisticated algorithms and computational instruments (e.g. neural networks, fuzzy logic, control systems).

One of the great challenges in conventional models and instruments in finance and economics is the volume of assumptions and corresponding requirements such as (but not limited to) normal distribution and convexity in problems like portfolio optimization, option pricing, algorithmic trading and risk management. After the 2008 financial crisis, it has been once again realized that traditional methods are not only incapable of recognizing irrationally elevated numbers, but these models are also very abstract considering the complexity of systems led by human judgment. There is an emerging need and a growing interest in CI solutions for financial engineering and economic analysis considering the gap arisen from simplifications and abstractions in traditional instruments such econometric analysis or financial methodologies with various assumptions (e.g. normality).

CI opens the way for completely new approaches like agent-based computational economics, in which market dynamics are modeled by evolving a large population of interacting heterogeneous agents.  Thanks to the advances in areas like evolutionary computation or fuzzy systems we can now model autonomous agents who have the capabilities to adapt, to learn, to have chances and to strategically interact with others and the surroundings.  Genetic programming or grammatical evolution open the possibilities for automatic trading rule identification, and artificial neural networks have major roles in domains like early bankruptcy prediction.

From a theoretical perspective, financial management and economics has established a powerful basis for understanding the monetary and economic phenomenon. By utilizing the capabilities of CI with proper integration of fundamental theories, a vast majority of common problems may be managed much efficiently and accurately. This special issue is dedicated to high-quality scholarly works and industrial solutions proposing original CI applications in finance and economics and/or addressing theoretical and practical challenges through solid empirical evidences.


Topics of Interest include
The aim of the special issue is to bring together the latest advances from both the theoretical and the application side at the intersection of computational intelligence in finance and economics. Authors are encouraged to submit high-quality original manuscripts in domains including (but not limited to):

Financial Engineering & Economics Applications
•   Agent-Based Computational Economics
•   Asset Pricing
•   Business Analytics
•   Algorithmic Trading
•   Electricity/Energy Markets
•   Big Data Finance & Economics
•   Machine Learning for Financial Analysis and Forecasting
•   Financial Data Mining
•   Financial Engineering
•   Financial Time Series Forecasting and Analysis
•   Economic and Financial Decision Making under Uncertainty
•   Artificial Immune Systems
•   Portfolio Management and Optimization
•   Market Simulation
•   Risk Management
•   Credit Risk Modelling
•   Commodity Markets
•   Pricing and Valuation
•   Term Structure Models
•   Trading Strategies
•   Pricing of Structured Securities
•   Asset Allocation
•   Trading Systems
•   Hedging Strategies
•   Risk Arbitrage
•   Sentiment Analysis and Behavioral Finance
•   Low Frequency / High Severity Event Modelling
•   Plasticity of Artificial Systems in Economics and Finance
•   Exotic Options

Computational intelligence techniques considered include (but not limited to):
•   Deep Learning and Artificial Neural Networks
•   Evolutionary Computation
•   Fuzzy Sets, Rough Sets, & Granular Computing
•   Financial Data Mining
•   Hybrid Systems
•   Metaheuristics
•   Support Vector Machines
•   Swarm Intelligence
•   Probabilistic Modeling/Inference
•   Intelligent Trading Agents
•   Trading Room Simulation
•   Time Series Analysis
•   Non-linear Dynamics
•   Rules and XBRL for Financial Engineering Applications
•   Semantic Web and Linked Data for Computer & Engineering Applications & Models


Submission Process
The IEEE CIM requires all prospective authors to submit their manuscripts in electronic format, as a PDF file. The maximum length for Papers is typically 20 double-spaced typed pages with 12-point font, including figures and references. Submitted manuscript must be typewritten in English in single column format. Authors of Papers should specify on the first page of their submitted manuscript up to 5 keywords. Additional information about submission guidelines and information for authors is provided at the IEEE CIM website.

Important Dates
Submission Deadline
December 31st, 2017

Notification of Review Results
March 15th, 2018

Submission of Revised Manuscripts
April 15th, 2018

Submission of Final Manuscript
June 15th, 2018

Special Issue Publication
Mid-October 2018
(November 2018 Issue)


okan7 (2)
Okan Duru
Nanyang Technological University, Singapore

Okan Duru is the Assistant Professor of Maritime Logistics and Finance at Nanyang Technological University, Singapore with a research focus on computational intelligence for predictive analytics in financial and economic phenomenon. He received his PhD degree from Kobe University, Japan on the long-term modelling of shipping freight rates. His research interests include fuzzy time series, dynamic model mining, learning algorithms for economic analysis with a special focus on transport economics and finance. He is also a member of Society for Computational Economics which is officially recognized by the American Economic Association (AEA). Okan Duru is particularly interested in intersecting topics between pure economics and computer science including economic forecasting, business analytics for economic analysis, predictive analytics and utilizing instrumental capacity of computer intelligence in common economic and financial problems. Okan Duru is the current vice-chair for the IEEE Technical Committee on Computational Finance and Economics.


Image result for robert golan
DBmind Technologies Inc., USA

Robert Golan is an Information/Rules Architect who is “hands on” with Service/Data Modeling while applying the Industry Standards. Robert is a specialist in the architecture, design, & development of Cloud based SOA Web/Restful Services for MDM/Data Warehouses with Business Intelligence and Business Rules/BPM integrations. Unstructured, Semi-structured, & Structured Data integrations with taxonomies, ontologies, vocabularies and Canonical/ Logical/Physical models are his specialty. The Data Sciences have been his focus since graduate studies where Robert has applied techniques from Machine Learning, Artificial/Computation Intelligence, Big Data, and Data Mining. Robert is a pioneer in the application of Computational Intelligence for Financial Engineering with emphasis on Advanced Algorithmic Trading strategies and Risk Management. Robert's research abilities coupled with his work experience, give him an outstanding ability to evaluate and apply new technologies and products. Robert has over thirty years of experience in designing, developing, and maintaining information technology systems while applying the needed information governance mechanisms. Project management, team leadership, and mentoring have been an integral part of Robert's project work. He has an extensive background with operating systems, communications, databases, and the internet. Robert’s domain knowledge cuts across the Financial, Pharmaceutical, HealthCare, Insurance, Energy, High Tech, and Agriculture industries. Robert Golan is the current chair for the IEEE Technical Committee on Computational Finance and Economics.


 David Quintana Montero
Carlos III de Madrid University, Spain

David Quintana holds Bachelor degrees in Business Administration and Computer Science. He has an M.S. in Intelligent Systems from Universidad Carlos III de Madrid and a Ph.D. in Finance from Universidad Pontificia Comillas (ICADE). He is currently and Interim Associate Professor with the Department of Computer Science at Universidad Carlos III de Madrid. There, he is part the bio-inspired algorithms group EVANNAI. His current research interests are mainly focused on applications of computational intelligence in finance and economics.


Image result for vasile palade
Coventry University, U.K.

Vasile Palade is a Reader in Pervasive Computing in the Faculty of Engineering and Computing and a member of the Cogent Computing Applied Research Centre at Coventry University. He previously held academic and research positions at the University of Oxford, UK (Departmental Lecturer in the Department of Computer Science), University of Hull, UK (Research Fellow in the Department of Engineering) and the University of Galati, Romania (Associate Professor in the Department of Computer Science and Engineering). He is the author of more than 120 papers in journals and conference proceedings as well as books on machine learning/computational intelligence and applications. His research interests include machine learning with various applications.

Tuesday 12 September 2017

5 Minutes with Dr. Gary Fogel

IEEE CIS Student Activities Subcommittee invites you to get to know the pioneers and experts in the Computational Intelligence through our new feature "5 minutes with..."
Our first "5 minutes with" focuses on pioneer Dr. Gary Fogel. Read all about Gary below and don't forget to say "Hello" at the next IEEE CIS Conference.
  1. What is your title, full name, and place of work?
    Dr. Gary Bryce Fogel, CEO Natural Selection, Inc., San Diego, California.
  2. What grade of member in CIS are you?
    IEEE Fellow, IEEE CIS Adcom member.
  3. How long have you been a member of CIS?
    Since CIS became a society in 2001.
  4. One reason why you are a member of CIS.
    To help the use of computational intelligence expand to include solutions to as many real-world problems as possible.
  5. What is your typical working day?
    I'm an early riser. I usually start my day at 5:45am and get to the office by about 7:30am. My work day usually ends around 5:30pm or 6pm. In between I am usually on a series of teleconferences with clients or having internal project meetings. I'm balancing many projects at the same time all the time at the office.
  6. What is your ideal weekend?
    Either spending time with family, or flying radio-controlled model sailplanes with friends. Check out YouTube videos for F3K discus launch gliding and you'll be hooked!
  7. Give one interesting fact about yourself:
    I've established 11 world records for radio-controlled aero models of various types.
  8. What are you reading, watching or listening to at the moment:
    I enjoy playing electric guitar and bass, mainly instrumental rock. My current favorites are Kiko Loureiro's and Andy Timmons.
  9. Favourite place:
    Anywhere above 3000m in the Sierra Nevada mountains, especially in areas with no cell phone coverage.
  10. Person you would most like to meet- past or present, real or fictional:
    Charles Darwin.
  11. What items would you take on a desert island and why:
    A really good inflatable raft. I'd love being on a desert island but there would come a time when I'd have to check how the office is going...

CFP: IEEE TCDS Special Issue on Neuro-Robotics Systems: Sensing, Cognition, Learning and Control (Nov 30)

AIM AND SCOPE
Neuro-robotics Systems (NRS) is a combined study of implementing human-like sensing, sensorimotor learning, coordination, cognition and control in autonomous robots, which can be integrated with cognitive capabilities, allowing them to imitate the way of humans and other living beings. NRS, a branch of neuroscience within robotics, is the current state-of-the-art research, as well as an important pillar in many countries’ brain projects. It assists the next generation of robots with embodied intelligence to be aware of themselves, interact with the environment and behave harmoniously with/as human beings. Therefore, it is a study to integrate recent breakthroughs in brain neuroscience, robotics and artificial intelligence in terms of new principles of understanding, modeling and developing robotic systems. This way of implementation will introduce smart and straightforward configuration of autonomous robots capable of handling complex tasks and adapting to unstructured environments. It will enable robots or robotic evices to not only do much more work, but also be smart enough to support or augment human abilities. As a bridge between neuroscience and robotics, it encourages researchers to study and understand how to define and develop the “brain” for future robots.
THEMES
This special issue aims at surveying the state of the art of the latest breakthrough technologies, new research results and developments in the area of NRS. We are particularly interested in papers that describe the formulation of various functions of NRS, including human-like sensing, fusion, cognition, learning and control, especially, the topics related to system sensing, multi-dimensional information fusion, and cognitive computation, sensorimotor learning and control technology. It provides a platform for interdisciplinary researchers to present their findings and latest developments of biomimetic mechatronics and robotics systems, covering relevant advances in engineering, computing, arts and bionic sciences. Areas of interest include, but are not limited to
  • Multi-modal perception, communication and interaction
  • Multi-modal neuromorphic computing
  • Brain-inspired end-to-end perception and control in robots
  • Knowledge representation, information acquisition, and decision making in neuro-robotics systems
  • Cognitive mechanism, and intention understanding in neuro-robotics systems
  • Affective and cognitive sciences for bio-mechatronics
  • Augmented cognitive robot systems, neuro-mechanical systems
  • Biomimetic modeling of perception and control in neuro-robotics systems
  • Brain-inspired development of rehabilitation robot systems, medical healthcare robot systems, prosthetic device systems, assistive robot systems, wearable robot systems for personal cooperative assistance
  • Sensorimotor coordination and control
  • Multi-modal intelligent learning and skill transfer system for multiple neuro-robotic systems
  • Robotic application oriented brain-inspired artificial intelligence algorithms and platforms on modeling, sensing, cognition, learning and control
SUBMISSION
Manuscripts should be prepared according to the “Information for Authors” of the journal found at http://cis.ieee.org/publications.html and submissions should be done through the IEEE TCDS Manuscript center: https://mc.manuscriptcentral.com/tcds-ieee and please select the category “SI: Neuro-Robotics Systems”.
IMPORTANT DATES
30. November 2017 – Deadline for manuscript submissions
28. February 2018 – Notification of authors
31. May 2018 – Deadline for revised manuscripts
31. July 2018 – Final decisions
February/March 2019 – Special Issue Publication
GUEST EDITORS
Zhijun Li
South China University of Technology, China
Email: zjli@ieee.org
Fei Chen
Italian Institute of Technology, Italy
Email: Fei.Chen@iit.it
Antonio Bicchi
University of Pisa, Italy
Email: antonio.bicchi@unipi.it
Yu Sun
University of Toronto, Canada
Email:sun@mie.utoronto.ca
Toshio Fukuda
Nagoya University/Meijo University, Japan
Email: tofukuda@nifty.com

Monday 11 September 2017

CFP: IEEE TETCI Special Issue on Large-scale Memristive Systems and Neurochips for Computational Intelligence (Oct 30)

I. AIM AND SCOPE

A special issue of the IEEE Transactions on Emerging Topics in Computational Intelligence will be dedicated to Large-Scale Memristive Systems and Neurochips for Computational intelligence. Original, unpublished research and application contributions matching the main theme of this special issue are welcome. Comprehensive tutorial and survey papers on Memristive Systems and Neurochips are considered for this special issue as well.

In the recent years, there has been a dramatic increase in the volume of research done to explore the application of memristors in various smart sensors, chips and systems, such as for implementing neural networks, deep learning, hierarchical temporal memories, intelligent memory arrays and brain-inspired neuromorphic systems. The small size, ease of programmability, low leakage currents, ability to maintain resistance states and CMOS compatibility make the memristor a useful device for neurochip implementations. The possibility of using memristors to mimic neural circuits as well as to implement learning memory for various spatio-temporal pattern recognition and neuromorphic computing applications makes it further a versatile device. However, in this early stages of development and exploration, the practical realisation of computational intelligence applications requires the development of in-depth theory, modelling, simulation and implementation of the memristors in large scale arrays and networks. This special issue aims to identify state of the art in the memristive systems and neurochips, and specifically encourages submissions that support the theory, algorithms and implementation of a wide range of emerging computational intelligence applications such as artificial life, artificial cellular networks, bio-inspired networks, and intelligence over the internet of things.

II. THEMES

We seek original papers with novel research contributions in all aspects of theory, simulations, algorithms, and implementation of complex memristive systems and neurochips, with a strong emphasis on emerging cross-disciplinary applications of computational intelligence. Topics of interest for this issue include, but are not limited to:

● Novel techniques for simulation and emulation of memristive systems and neurochips
● Bioinspired circuits, algorithms and systems utilizing memristive arrays
● Intelligent sensory signal processing algorithms for neuro-memristive systems
● Large-scale memristive systems and neurochips for internet of things
● Neuromorphic models, algorithms and systems, and its computational intelligence applications
● Intelligent memory systems, cognitive architectures and its implementations
● Large-scale implementations and simulations of neurochips
● Spatio-temporal analysis with neurochips and memory systems
● Deep learning architectures, theories, systems and its implementations
● Neurochip systems of systems implementation, and architecture optimisations

III. IMPORTANT DATES

Submission deadline: October 30, 2017
Author notification: January 15, 2017
Revision: March 15, 2018
Final version: April 15, 2018

IV.GUEST EDITORS

Alex Pappachen James Nazarbayev University, Kazakhstan apj@ieee.org
Khaled Nabil Salama King Abdulla University of Science and Technology (KAUST), Saudi Arabia khaled_salama@ieee.org
Hai (Helen) Li Duke University, USA hai.li@duke.edu
Dalibor Biolek University of Defence Brno, Czech Republic dalibor.biolek@unob.cz
Giacomo Indiveri University of Zurich and ETH Zurich, Switzerland giacomo@ini.uzh.ch
Leon Ong Chua University of California, Berkeley, USA chua@berkeley.edu