Tuesday 30 May 2017


IEEE Transactions on Neural Networks and Learning Systems; Volume 28, Issue 6, June 2017.
Posted by: Haibo He (ieeetnnls@gmail.com)
Date submitted: June 1, 2017

The following articles appeared in the latest issue of IEEE Transactions on Neural Networks and Learning Systems: Volume 28, Issue 6, June 2017.

This issue published papers on graph-based learning, sparse coding, adaptive control, quantum ensemble classification, spiking neural networks, deep neural networks, radial basis function networks, support vector machines, kernel methods, among others. We welcome your submissions to IEEE TNNLS.

These articles can be retrieved on IEEE Xplore:
or directly by clicking the individual paper URL below.

IEEE Transactions on Neural Networks and Learning Systems;
Volume 28, Issue 6, June 2017.

1. Holographic Graph Neuron: A Bioinspired Architecture for Pattern Processing
Author(s): Denis Kleyko; Evgeny Osipov; Alexander Senior; Asad I. Khan; Yaşar Ahmet Şekerciogğlu
Page(s): 1250 - 1262

2. Robust Joint Graph Sparse Coding for Unsupervised Spectral Feature Selection
Author(s): Xiaofeng Zhu; Xuelong Li; Shichao Zhang; Chunhua Ju; Xindong Wu
Page(s): 1263 - 1275

3. Rate of Convergence of the FOCUSS Algorithm
Author(s): Kan Xie; Zhaoshui He; Andrzej Cichocki; Xiaozhao Fang
Page(s): 1276 - 1289

4. Action and Event Recognition in Videos by Learning From Heterogeneous Web Sources
Author(s): Li Niu; Xinxing Xu; Lin Chen; Lixin Duan; Dong Xu
Page(s): 1290 - 1304

5. Mapping Temporal Variables Into the NeuCube for Improved Pattern Recognition, Predictive Modeling, and Understanding of Stream Data
Author(s): Enmei Tu; Nikola Kasabov; Jie Yang
Page(s): 1305 - 1317

6. Adaptive Neural Control of Uncertain MIMO Nonlinear Systems With State and Input Constraints
Author(s): Ziting Chen; Zhijun Li; C. L. Philip Chen
Page(s): 1318 - 1330

7. Co-Operative Coevolutionary Neural Networks for Mining Functional Association Rules
Author(s): Bing Wang; Kathryn E. Merrick; Hussein A. Abbass
Page(s): 1331 - 1344

8. Quantum Ensemble Classification: A Sampling-Based Learning Control Approach
Author(s): Chunlin Chen; Daoyi Dong; Bo Qi; Ian R. Petersen; Herschel Rabitz
Page(s): 1345 - 1359

9. A Regularizer Approach for RBF Networks Under the Concurrent Weight Failure Situation
Author(s): Chi-Sing Leung; Wai Yan Wan; Ruibin Feng
Page(s): 1360 - 1372

10. Clustering Through Hybrid Network Architecture With Support Vectors
Author(s): Emrah Ergul; Nafiz Arica; Narendra Ahuja; Sarp Erturk
Page(s): 1373 - 1385

11. Design and Application of a Variable Selection Method for Multilayer Perceptron Neural Network With LASSO
Author(s): Kai Sun; Shao-Hsuan Huang; David Shan-Hill Wong; Shi-Shang Jang
Page(s): 1386 - 1396

12. Robustly Fitting and Forecasting Dynamical Data With Electromagnetically Coupled Artificial Neural Network: A Data Compression Method
Author(s): Ziyin Wang; Mandan Liu; Yicheng Cheng; Rubin Wang
Page(s): 1397 - 1410

13. Efficient Training of Supervised Spiking Neural Network via Accurate Synaptic-Efficiency Adjustment Method
Author(s): Xiurui Xie; Hong Qu; Zhang Yi; Jürgen Kurths
Page(s): 1411 - 1424

14. Sparseness Analysis in the Pretraining of Deep Neural Networks
Author(s): Jun Li; Tong Zhang; Wei Luo; Jian Yang; Xiao-Tong Yuan; Jian Zhang
Page(s): 1425 - 1438

15. Barrier Function-Based Neural Adaptive Control With Locally Weighted Learning and Finite Neuron Self-Growing Strategy
Author(s): Zi-Jun Jia; Yong-Duan Song
Page(s): 1439 - 1451

16. Label Propagation via Teaching-to-Learn and Learning-to-Teach
Author(s): Chen Gong; Dacheng Tao; Wei Liu; Liu Liu; Jie Yang
Page(s): 1452 - 1465

17. Optimized Kernel Entropy Components
Author(s): Emma Izquierdo-Verdiguier; Valero Laparra; Robert Jenssen; Luis Gómez-Chova; Gustau Camps-Valls
Page(s): 1466 - 1472

18. Quantized Iterative Learning Consensus Tracking of Digital Networks With Limited Information Communication
Author(s): Wenjun Xiong; Xinghuo Yu; Yao Chen; Jie Gao
Page(s): 1473 - 1480

19. Biomimetic Hybrid Feedback Feedforward Neural-Network Learning Control
Author(s): Yongping Pan; Haoyong Yu
Page(s): 1481 - 1487

Monday 22 May 2017

Call for Participation: 12th International Workshop on Semantic and Social Media Adaptation and Personalization (SMAP 2017)

July 9-10, 2017, Bratislava, Slovakia
Collocated with UMAP 2017
Organized by Foundation for Development of Informatics

*List of accepted papers: http://smap2017.org/accepted-papers/

*Important dates:
SMAP 2017 Early registration: May 26, 2017
SMAP 2017 Workshop:          July 9-10, 2017

*Aim and Sessions:
SMAP 2017 aims to address several issues of semantic and social multimedia technologies and their use in content creation, media adaptation and user profiling. SMAP 2017 has the support of the IEEE Computational Intelligence Society technical co-sponsorship.

In addition to the regular track, two Special Sessions are organised at SMAP 2017: 

*Special session on Personalized delivery of cultural heritage content
Digital cultural heritage is now a mature field, in which information technologies are used in the service of preserving cultural heritage. The digital form of resources allows for the exploitation of advances in data analytics, semantics, information retrieval, user interaction, profiling and personalization in order to develop new, exciting and stimulating exhibitions and cultural/educational/touristic experiences. The session is broad in scope, with the caveat that emphasis should be on the link between cultural heritage and personalization techniques.

*Special Session on Multimodal affective analysis for human-machine interfaces and learning environments
Affective analysis is a broad research area that focuses on the recognition, interpretation, processing and simulation of human affect, i.e., feelings or emotions. During the last years many efforts in the fields of content understanding and human-machine interaction have turned towards a more human-centered approach and complement traditional semantic-based ones by enhancing them with the users’ affective state while interacting with machines (typically computers, avatars and robots).

The registration for SMAP 2017 is handled by Action M Agency, conference organizer operating in Prague, Czech Republic. You will find all registration details at the following address: http://smap2017.org/registration/

SMAP 2017 will be held at Slovak University of Technology in Bratislava (Slovakia) in the new building of the Faculty of Informatics and Information Technologies (Ilkovičova 2, 841 04, Bratislava). The workshop is collocated with UMAP 2017, the 25th conference on User Modeling, Adaptation and Personalization.

Bratislava is well connected to the world through neighboring Vienna airports, and also lies in close proximity to other major cities such as Prague and Budapest, from which it is easily accessible by trains.

Maria Bielikova, Slovak University of Technology in Bratislava
Marian Simko, Slovak University of Technology in Bratislava

Ioannis Anagnostopoulos, University of Thessaly
Iraklis Paraskakis, The University of Sheffield, International Faculty  CITY College, Greece

Sebastien Laborie, University of Pau

Milena Zeithamlova, Action M Agency

Patrik Hlavac, Slovak University of Technology in Bratislava

Ioannis Anagnostopoulos, University of Thessaly
Maria Bielikova, Slovak University of Technology in Bratislava
Sébastien Laborie, University of Pau
Martin Lopez-Nores, University of Vigo
Phivos Mylonas, Ionian University
Yannick Naudet, Luxembourg Institute of Science and Technology
Nicolas Tsapatsoulis, Cyprus University of Technology
Manolis Wallace, University of the Peloponnese

Friday 19 May 2017

Call for submissions: IEEE CIS competition on “Telling a Story: How your Computational Intelligence Research benefits Society and Humanity”

Organised by IEEE CIS Competitions subcommittee, IEEE CIS Student Activities and IEEE CIS Pre College Activities

Launch Date: 1st May 2017
Closing Date: 1st October 2017
Announcement of Winners: IEEE SSCI, Hawaii, NOVEMBER 27 to DECEMBER 1, at the Awards Ceremony
Category 1: Best Video
Category 2: Best Interactive Tutorial / Demo
Prizes sponsored by the IEEE computational intelligence Society.
Prizes are for each category
First Prize:   $500 USD
Second prize: $300 USD
Third Prize: $200 USD

Competition Background
A core purpose of the IEEE Computational Intelligence Society is to foster technological innovation and excellence for the benefit of society and humanity.
As student members of the Society, your research is fundamental to the future of technological developments that can make a difference to people’s lives.
The IEEE Computational Intelligence Society invites you to tell your own research story using any type of artefact which must be accessible online i.e. (a short video presentation (max 5 minutes), an online game, an interactive piece of software which demos your work etc.
The Artefact must be able to explain the main ideas to pupils aged 14 – 18 and convey why working in the field of computational intelligence is exciting, a part of our everyday lives and be used to inspire others.

Competition Details
To enter the competition:
Students must submit an artefact about their own research in the field of computational intelligence   using any type of artefact which must be accessible online i.e. (a short video presentation (max 5 minutes), an online game, an interactive piece of software which demos their work.
Students can submit to one Artefact to one category only. The Categories are

Category 1: Best Video
Category 2: Best Interactive Tutorial / Demo

Prizes will be awarded for each category.   

1. The student must be an IEEE CIS student member.
2. Each student must register on the competition website.  Registration will open soon.
3. The type of artefact and its category must be selected. One submission allowed per student.
4. Each student must submit:
  • A short report (max 2 pages) providing the following information
    • Name of Student, Educational Institution, Supervisory Team, Start and End Date of the research Project, Brief Summary of Research Project, Type of Artefact, Name of Artefact, brief description of artefact, A statement of how the research benefits society and humanity.
  • In addition
    • for web-based game/ interactive demos submissions: Submit a link (optionally encrypted by a password) to their web-based game or a web-based interactive demo. Web-based games should be able to be run in any browser.
    • A ZIP file containing all the files (including code) related to the web-based game or a web-based interactive demo.
    • A set of instructions on how to use the application / run the demo / play the game. This will include what programming platforms and languages were used for development.
    • All items should be submitted as a zip file.
  • For short video presentations (max 5 minutes in length, the video should be uploaded onto YouTube and a link should be submitted.  

For more information please contact Dr Keeley Crockett, chair IEEE CIS Student Activities Subcommittee email: K.Crockett@mmu.ac.uk

Wednesday 17 May 2017

CFP: TETCI special issue on Data Driven Computational Intelligence for eGovernance, Socio-Political and Economic Systems


E-Governance is the application of electronic, information and communication technologies in order to facilitate public services, support government administration and democratic processes, and strengthen the relations among citizens, civil society and the private sector. E-governance aims to utilize digital tools and models to promote the interaction between three key partners of modern societies: government, citizens and business. Optimising these interactions can help to facilitate political, social, economic stability and prosperity.

Significant breakthroughs in the development of nature inspired Computational Intelligence (CI) techniques allow for the utilization and analysis of vast amounts of data generated from different sources such as transactions of citizens with government services, human interaction with social networks and the use of interconnected smart pervasive devices. Many political, social and economic systems can be understood through bottom up computational methodologies such as agent based modelling and can equally be driven by various realworld data sources fraught with uncertainties pertaining to human decision making, knowledge perception and agreement models that need to be handled using fuzzy and probabilistic reasoning approaches. Top down machine learning techniques such as deep learning can be used to discover complex patterns and correlations in historical data for modelling and predicting consequences of economic shocks, utility of municipal services or changing political sentiments. Advances in evolutionary technique can provide a means for optimizing e-governance policies and strategies by simulating their impact on aspects such as labour and employability or modelling complex negotiation processes. CI approaches can be more broadly applied to model population mobility, economic growth, social behaviour, public health, security risks, education, welfare, geopolitics and environmental concerns.


The aim of this Special Issue (SI) is to develop novel
computational tools and design systems to exploit the vast
amounts of data generated continuously through the
interaction of citizens with the government, and the
surrounding environment and provide optimized e-governance
services. The scope of this SI includes, but is not limited to:

  •  Simulation models for socio-political economic systems
  •  Measuring feedback and effects of new political initiatives
  •  Sentiment analyses on utility of governance systems, public and commercial services
  •  Facilitating citizen participation in policy decision making
  •  Data analysis, visualization and modelling of social political, fiscal and threat associated behaviours.
  •  Information retrieval, secure storage and recovery of data. 

The special issue welcomes high quality contributions in the form of full or short papers. Manuscripts should be prepared according to the “Information for Authors” section of the journal found at http://cis.ieee.org/ieee-transactions-onemerging-topics-in-computational-intelligence.html and submissions should be done through the journal submission website: https://mc.manuscriptcentral.com/tetci-ieee, by selecting the Manuscript Type of “DDCIeGov” and clearly marking “Data Driven Computational Intelligence for eGovernance, Socio-Political and Economic Systems 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. 


5 th June 2017: Submission of Manuscripts
7 th August 2017: Notification of Review Results (R1) 
2 nd October 2017: Submission of Revised Manuscripts 
6 th November 2017: Final Review Results Notification (R2) 
4 th December 2017: Submission of Final Manuscripts 


Dr Faiyaz Doctor, School of Computing Electronics and Mathematics, Faculty of Engineering, Environment and Computing, Coventry University, Coventry, UK Faiyaz.doctor@coventry.ac.uk 

Dr Edgar Galvan-Lopez, TAO Project, INRIA Saclay & LRI - Univ. Paris-Sud and CNRS, Orsay, France, edgar.galvan@inria.fr 

Professor Edward Tsang, Centre for Computational Finance and Economic Agents (CCFEA), School of Computer Science and Electronic Engineering, University of Essex, Essex, UK edward@essex.ac.uk

Monday 15 May 2017

CFP: IEEE International Conference on Machine Learning and Applications (ICMLA)

Cancun, Mexico
Dec 18 – 21, 2017

ICMLA 2017 aims to bring together researchers and practitioners to present their latest achievements and innovations in the area of machine learning (ML).
The conference provides a leading international forum for the dissemination of original research in ML, with emphasis on applications as well as novel algorithms and systems. Following the success of previous ICMLA conferences, the conference aims to attract researchers and application developers from a wide range of ML related areas, and the recent emergence of Big Data processing brings an urgent need for machine learning to address these new challenges. The conference will cover both machine learning theoretical research and its applications. Contributions describing machine learning techniques applied to real-world problems and interdisciplinary research involving machine learning, in fields like medicine, biology, industry, manufacturing, security, education, virtual environments, games, are especially encouraged. The technical program will consist of, but is not limited to, the following topics of interest:

Statistical learning; Neural network learning; Learning through fuzzy logic; Learning through evolution; Reinforcement learning; Multi-strategy learning; Cooperative learning; Planning and learning; Multi-agent learning; Online and incremental learning; Scalability of learning algorithms; Inductive learning; Inductive logic programming; Bayesian networks; Support vector machines; Case-based reasoning; Grammatical inference; Knowledge acquisition and learning; Knowledge discovery in databases; Knowledge intensive learning; Knowledge representation and reasoning  ; Machine learning for information retrieval; Learning through mobile data mining; Machine learning for web navigation & mining; Text and multimedia mining; Feature extraction and classification; Distributed and parallel learning algorithms and applications; Computational learning theory; Theories and models for plausible reasoning; Cognitive modeling; Hybrid learning algorithms; Multi-lingual knowledge acquisition and representation

Applications of machine learning in:

Medicine and health informatics; Bioinformatics and systems biology; Industrial and engineering applications; Security; Smart cities; Game playing and problem solving; Intelligent virtual environments; Economics; business and forecasting.

The conference will include a number of interesting keynote plenary talks, which will be announced on the conference web site as arrangements are finalized. Previous invited speakers included numerous fellows of IEEE, AMIA, AAAS, AAAI, etc. Prospective authors are invited to submit eight pages manuscript describing original work. The manuscript has to be written in English and in PDF format. Please visit the conference website for details: http://www.icmla-conference.org/icmla17/

Key dates:

Paper Submission Deadline: Main Conference:   July 6, 2017
Special Sessions/Workshops/Challenges:        August 6, 2017
Notification of Acceptance:                         September 9, 2017
Camera-ready Papers:                                        October 1, 2017

Organizing Committee:

General Chair:
Bill Chen (Wayne State University)

Conference Chair:
Bo Luo (The University of Kansas)

Program Co-Chairs:
Vasile Palade (Conventry University)
Feng Luo (Clemson University)

Workshop and Special Session Chair:
Yanjie Fu (Missouri University of Science and Technology)

Publicity Chair:
Roozbeh Razavi-Far (University of Windsor)


It will be a pleasure if you can participate in ICMLA 2017 conference. Thanks for your attention, and we hope to see you in Cancun, Mexico, during the ICMLA 2017 event.

CFP: TETCI special issue on Computational Intelligence for Cloud Computing


With the rapid advancement of modern technology, the existing communication models and computing environments have changed immensely. Cloud computing has emerged as an exciting new computing environment where computing infrastructure, platforms, and software application services are offered at low cost from remote very-large-scale data centres accessed over the Internet. Cloud computing shares some characteristics common to parallel computing, but differs in that it uses virtualization for resource management. Since it offers huge savings in business costs, cloud computing has recently received large amounts of attention and continued to be of high priority for researchers and developers in both academia and industry. 

Traditional Computational Intelligence (CI) methods have played important roles in solving a variety of networking and computing tasks in cyberspace in a reliable, unbiased, and automatic manner. The emergence of cloud computing environments poses a number of difficulties, complex issues in optimization and learning as well as other aspects. They call for new paradigms because the arising problems have become intractable when dealt with the use of traditional methods. CI research could provide important technical innovations to develop intelligent solutions for the new computing environments and their real world applications. The development of new CI theories and techniques for cloud computing has attracted significant amount of attention recently from academia, industry, and government as well. 

The aims of this special issue are (1) to present the state-of-the-art research on utilizing novel CI techniques for cloud computing environments, and (2) to provide a forum for experts to disseminate their recent advances and views on future perspectives in the field.


In this special issue, we will invite papers that present new CI theories, methods and techniques applied to cloud computing. We particularly encourage papers demonstrating novel CI strategies to new types of cloud computing domains such as mobile cloud computing, social cloud computing, etc. Applications may be drawn by investigating the usage of CI for all aspects of the cloud computing system, including the architecture analysis, system design, prototype implementation, performance optimization, operation maintenance, and security management. 

Specific topics may include the application of CI to the following areas: 
  • Resource allocation and scheduling in cloud services 
  • System optimization in cloud environment 
  • Cloud system design
  • Energy efficiency in cloud computing
  • Cloud management (configuration, performance, and capacity) 
  • Storage, data, and analytics clouds  
  • Virtual machine placement in cloud infrastructure
  • Computation partitioning in mobile cloud computing  
  • Resource management in mobile cloud environments  
  • Security and privacy in cloud computing

Manuscripts should be prepared according to the “Information for Authors” section of the journal found at http://cis.ieee.org/ieee-transactions-on-emerging-topics-in-co mputational-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 for Cloud Computing” and clearly marking “Computational Intelligence for Cloud Computing 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.


Submission deadline: May 31, 2017
Author notification (R1): August 1, 2017
Revision: September 1, 2017
Author notification (R2): October 1, 2017
Final version: November 1, 2017 


Dr Hui Cheng, Department of Computer Science, Liverpool John Moores University, Liverpool, UK H.Cheng@ljmu.ac.uk 
Prof Shengxiang Yang, School of Computer Science and Informatics, De Montfort University, Leicester, UK syang@dmu.ac.uk 
Prof Xin Yao, Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China, and School of Computer Science, University of Birmingham, Birmingham, UK xiny@sustc.edu.cn 
Prof Mengjie Zhang, School of Engineering and Computer Science, Victoria University of Wellington, New Zealand Mengjie.Zhang@ecs.vuw.ac.nz

Saturday 13 May 2017

CFP: IEEE TNNLS Special Issue on Intelligent Control through Neural Learning and Optimization for Human Machine Hybrid Systems

During the recent decades, there are a vast number of learning methods for designing intelligent controllers for human machine hybrid systems. However, a further consideration not only is guaranteeing the control stability, but is optimality based on a predefined cost function to determine the performance of the human machine hybrid systems. Therefore, we are faced with a need for improved control schemes, which not only achieve the stability of the human machine hybrid systems, but also keep the cost of the systems as small as possible. The special issue addresses a broad spectrum of topics ranging from deterministic and stochastic intelligent control design for various human machine hybrid systems such as unmanned aerial vehicles, intelligent quadruped robots, industrial robots, robotic exoskeletons, biped robots, wheeled balance transporters, to the optimization of the learning algorithm. Special attention should be given to how to optimize controller design, achieve the high accurate performance for the human machine interactions, and
handle nonlinearities and the unknown system dynamics. This includes modeling, learning control, neural network adaptations, iterative learning, deep learning, reinforcement learning, dynamic programming and testing the effectiveness of the controllers. The special issue publishes original papers of innovative ideas and concepts, new discoveries and improvements, and novel applications to the field of intelligent control for human machine hybrid systems.

Topics explored in this special issue include, but are not limited to:

• Learning and Optimizations for the intelligent control;
• Adaptive dynamic programming for human machine hybrid systems and their applications;
• Iterative learning control for human machine hybrid systems and their applications;
• Deep Learning for human machine interactions;
• Reinforcement learning to handle nonlinearities for human machine hybrid systems;
• Learning control design for intelligent robots;
• High accurate tracking control via learning for multi-robot systems and applications;
• Modeling and learning control for humanoid robots and applications;
• Identification and learning control design for quadruped robots;
• System design and learning control for industrial robots;
• Learning control and optimizations for exoskeletons;
• Learning control and balance analysis for wheeled balance transporters;
• Learning control and optimizations for aerial vehicles;
• Learning control and stability analysis for humanoid robots or quadruped robots;
• Modeling, identification and optimizations via learning;
• Neural network control and practical applications in model-free environment;
• New applications of learning control for human machine hybrid systems.


November 15, 2017 – Deadline for manuscript submissions
February 15, 2018 – Information about manuscript acceptance
April 15, 2018 – Submission of revised paper
June 15, 2018 – Final decisions
October 15, 2018 – Estimated publication date

Wei He, School of Automation and Electrical Engineering, University of Science and Technology Beijing, China
Changyin Sun, School of Automation, Southeast University, Nanjing, China
Donald C. Wunsch, Department of Electrical & Computer Engineer, Missouri University of Science & Technology, US
Richard Yi Da Xu, School of Computing and Communications, University of Technology Sydney, Australia


  1. Read the information for Authors at http://cis.ieee.org/tnnls.
  2. Submit your manuscript at the TNNLS webpage (http://mc.manuscriptcentral.com/tnnls) and follow the submission procedure. Please, clearly indicate on the first page of the manuscript and in the cover letter that the manuscript is submitted to the special issue on Intelligent Control through Neural Learning and Optimization for Human Machine Hybrid Systems. Send an email to the leading editor Prof. Wei He (weihe@ieee.org) with subject TNNLS special issue submission to notify about your submission.
  3. Early submissions are welcome. We will start the review process as soon as we receive your contributions.

CFP: IEEE TNNLS Special Issue on Discriminative Learning for Model Optimization and Statistical Inference

Model optimization and statistical inference have played a central role in various applications of computational intelligence, data analytics, and computer vision. Traditional model-centric learning approaches require properly crafted optimization and inference algorithms, as well as carefully tuned parameters. Recently, the discriminative learning technique has demonstrated its power for process-centric learning. The resulting solutions are closely related to a variety of statistical and optimization models such as sparse representation, structured regression, and conditional random fields, and are empowered by effective computational techniques such as bi-level optimization and partial differential equations (PDEs). Moreover, many deep learning models has been shown to be closely tied with discriminative learning models. For example, a problem-specific deep architecture can be formed by unfolding the model inference as an iterative process, whose parameters can be jointly learned from training data with a discriminative loss. Such a viewpoint motivates the incorporation of domain expertise and problem structures into designing deep architectures, and helps the interpretation and performance improvement of deep models.

This special issue aims at promoting first-class research along this direction, and offers a timely collection of information to benefit the researchers and practitioners. We welcome high-quality original submissions addressing both novel theoretical and modeling progress, and real-world applications that benefit discriminative learning for model optimization and statistical inference. 

Topics of interests include, but are not limited to:
  • Task-driven learning for model optimization and/or statistical inference.
  • Novel architectures and algorithms for bi-level optimization and/or PDEs .
  • Problem-specific deep architectures for solving model optimization and statistical inference.
  • Integration of optimization-based, statistical learning, and inference models with deep learning models.
  • Sparse representation motivated deep architectures.
  • Structured regression motivated deep architectures.
  • Conditional random forest motivated recurrent neural networks.
  • Novel interpretative frameworks on the working mechanism of representative deep learning models. 
  • Theoretical analysis of deep learning models and algorithms: convergence, optimality, generalization, stability, and sensitivity analysis.
  • Applications based on the above described models and algorithms: (1) image enhancement, restoration and synthesis; (2) optical flow, stereo matching, camera localization, and normal estimation; (3) visual recognition, detection, and segmentation, and scene understanding; (4) pattern classification, clustering and dimensionality reduction; (5) medical image analysis and other novel application domains.

  15 July 2017 – Deadline for manuscript submission
  30 September 2017 – Reviewer’s comments to authors
  15 November 2017 – Deadline for submitting revised manuscripts
  30 December 2017 – Final decision of acceptance to authors
  30 April 2018- Tentative publication date

  Wangmeng Zuo, Harbin Institute of Technology, China.
  Zhangyang (Atlas) Wang, Texas A&M University, USA.
  Xi Peng, Institute for Infocomm, A*STAR, Singapore.
  Ling Shao, University of East Anglia, UK.
  Danil Prokhorov, Toyota Research Institute North America, USA.
  Horst Bischof, Graz University of Technology, Austria.

Read the Information for Authors at http://cis.ieee.org/tnnls.
Submit your manuscript at the TNNLS webpage (http://mc.manuscriptcentral.com/tnnls) and follow the submission procedure. 
Please, clearly indicate on the first page of the manuscript and in the cover letter that the manuscript is submitted to this special issue. Send an email to the leading guest editor, Prof. Wangmeng Zuo (wmzuo@hit.edu.cn), with subject “TNNLS special issue submission” to notify about your submission. 
Early submissions are welcome. We will start the review process as soon as we receive your contributions.