The First International Workshop on Deep and Transfer Learning DTL2018

征稿已开启

已截稿

注册已开启

已截止

活动简介

Deep learning approaches have caused tremendous advances in many areas of computer science. Deep learning is a branch of machine learning where the learning process is done using deep and complex architectures such as recurrent convolutional artificial neural networks. Many computer science applications have utilized deep learning such as computer vision, speech recognition, natural language processing, sentiment analysis, social network analysis, and robotics. The success of deep learning enabled the application of learning models such as reinforcement learning in which the learning process is only done by trial-and-error, solely from actions rewards or punishments. Deep reinforcement learning come to create systems that can learn how to adapt in the real world. As deep learning utilizes deep and complex architectures, the learning process usually is time and effort consuming and need huge labeled data sets. This inspired the introduction of transfer and multi-task learning approaches to better exploit the available data during training and adapt previously learned knowledge to emerging domains, tasks, or applications.
Despite the fact that many research activities is ongoing in these areas, many challenging are still unsolved. This workshop will bring together researchers working on deep learning, working on the intersection of deep learning and reinforcement learning, and/or using transfer learning to simplify deep leaning, and it will help researchers with expertise in one of these fields to learn about the others. The workshop also aims to bridge the gap between theories and practices by providing the researchers and practitioners the opportunity to share ideas and discuss and criticize current theories and results.

Proceedings of the workshops will be published by the IEEE Conference Publishing Services (CPS) and will be submitted for inclusion in the IEEE-Xplore and the IEEE Computer Society (CSDL) digital libraries.

组委会

General co-Chairs:

Mohammad Alsmirat, Jordan University of Science and Technology, Jordan.

Technical Program co-Chairs:

Mahmoud Al-Ayyoub, Jordan University of Science and Technology, Jordan
Thar Baker, Liverpool John Moores University, Liverpool, UK
Paulo R. L. Gondim, University of Brasilia, Brazil

Publicity Chairs:

Gizem Gültekin Varkonyi, University of Szeged, Hungary.
Suleyman Eken, Kocaeli University, Turkey.

Invited Speaker and Panel Chair:

Gizem Gültekin Varkonyi, University of Szeged, Hungary.
Rossi Kamal, Shanto-Mariam University of Creative Technology, Bangladesh

Steering Committee:

Mohammad Alsmirat, Jordan University of Science and Technology, Jordan.
Jim Jansen , Qatar Computing Research Institute, HBKU, Qatar and The Pennsylvania State University, USA
Mahmoud Al-Ayyoub, Jordan University of Science and Technology, Jordan
Thar Baker, Liverpool John Moores University, Liverpool, UK
Paulo R. L. Gondim, University of Brasilia, Brazil
Yaser Jararweh, Jordan University of Science and Technology, Jordan.

Technical Programme Committee:

Izzat Alsmadi, Texas A&M San Antonio, USA (Izzat.Alsmadi@tamusa.edu)
Mustafa Jarrar, Birzeit University, Palestine
Rossi Kamal, Shanto-Mariam University of Creative Technology, Bangladesh
Ashraf Elnagar, ML&ALP Research Lab, University of Sharjah, UAE
Mohamed Abdel-Maguid, University Campus Suffolk, UK
Jie Gao, Stony Brook University, USA
Bhavani Thuraisingham, The University of Texas at Dallas, USA
Elhadj Benkhelifa, Staffordshire University, UK.
Abdullah Khreishah, New Jersey Institute of Technology, USA.
Bas Geerdink, ING, Netherlands
Bhavani Thuraisingham, The University of Texas at Dallas, USA
Mohammed Naji Al-Kabi, ZU, Jordan
Kami Makki, Lamar University, USA
Al-Sakib Khan Pathan, International Islamic University Malaysia (IIUM), Malaysia.
Mahmoud Al-Ayyoub, Jordan University of Science and Technology, Jordan.
Marcio Lobo Netto, EPUSP, Brazil
Heider Wahsheh, KSA
Yaser Jararweh, Jordan University of Science and Technology, Jordan
Mladen Vouk, N.C. State University, USA.

征稿信息

重要日期

2018-07-15

初稿截稿日期

2018-08-25

初稿录用日期

We invite the submission of original papers on all topics related to deep learning, deep reinforcement learning, and transfer and multi-task learning, with special interest in but not limited to:

Deep learning for innovative applications such machine translation, computational biology
Deep Learning for Natural Language Processing
Deep Learning for Recommender Systems
Deep learning for computer vision
Deep learning for systems and networks resource management
Optimization for Deep Learning
Deep Reinforcement Learning
o Deep transfer learning for robots
o Determining rewards for machines
o Machine translation
o Energy consumption issues in deep reinforcement learning
o Deep reinforcement learning for game playing
o Stabilize learning dynamics in deep reinforcement learning
o Scaling up prior reinforcement learning solutions
Deep Transfer and multi-task learning:
o New perspectives or theories on transfer and multi-task learning
o Dataset bias and concept drift
o Transfer learning and domain adaptation
o Multi-task learning
o Feature based approaches
o Instance based approaches
o Deep architectures for transfer and multi-task learning
o Transfer across different architectures, e.g. CNN to RNN
o Transfer across different modalities, e.g. image to text
o Transfer across different tasks, e.g. object recognition and detection
o Transfer from weakly labeled or noisy data, e.g. Web data
Datasets, benchmarks, and open-source packages

作者指南

Authors are requested to submit papers reporting original research results and experience. The page limit for full papers is 6 pages. Papers should be prepared using IEEE two-column template.

IEEE Computer Society Proceedings Author Guidelines are available at: IEEE Guidelines Link

Submitted research papers may not overlap with papers that have already been published or that are simultaneously submitted to a journal or a conference. All papers accepted for this conference are peer-reviewed and are to be published in the conference proceedings by the IEEE Computer Society Conference Publishing Service (CPS), and indexed by IEEE Xplore Digital Library