Emerging Innovations in Deep Learning

Special Issue: Emerging Innovations in Deep Learning

Introduction

Deep learning is a machine learning technique that teaches computers to do what comes naturally to humans: learn by example. It has been extensively applied to various areas, and will produce dramatic impact to our daily life. However, applying deep learning to solve problems will encounter some challenges. Deep learning algorithms require a large and diverse range of data, and a large number of parameters need to be tuned. Also, there are overfitting problems when a well-trained deep learning model is used , hence not easily applied in other areas. Moreover, the training process of deep learning is still a black box, and how they learning and how they deduce conclusions are diffcult to be understood by the researchers.

The objective of this issue intends to bring together academicians, researchers, and practitioners to highlight the emerging trends, applications and research challenges in the development of theoretical, methodological, and practical aspects of Deep Learning , along with innovative or interdisciplinary approaches that will benefit both the academia and the industry. The perspective authors are invited to submit their works online through:

http://ojs.imeti.org/index.php/IJETI/about/submissions#onlineSubmissions

by following the Author’s guideline available at:

http://ojs.imeti.org/index.php/IJETI/about/submissions#authorGuidelines.

During submission, please choose Special Issue: Emerging Innovations in Deep Learning 

 

Topics

The topics of interest include, but are not limited to

  • New methods/Algorithms for Deep Learning

  •  New learning methods for established Deep Learning architectures

  • Faster and more robust methods for learning of deep models

  • Methods for non-established Deep Learning models

  • Reasoning of Input-Output Behavior of Deep Learning Models

  • Deep Learning Classifiers combined with Active Learning

  • Evolutionary-based optimization and tuning of Deep Learning models

  • Hybrid learning schemes (deterministic with heuristics-based, memetic)

  •  Incremental learning methods for self-adaptive deep models

  • Evolving techniques for Deep Learning systems

  • Big Data Analysis for Deep Learning

  • Context-Awareness and Intelligent Environment Applications

  • Intelligent Human-Computer Interaction

  • Intelligent E-Learning & Tutoring

  • IoT Application by Deep Learning

  • Speech recognition and image recognition by by Deep Learning

  • Smart Healthcare by Deep Learning

  • Biological Computing by Deep Learning

  • Smart Living and Smart Cities by Deep Learning

  • Information Security by Deep Learning

  • Others related topics of Deep Learning

Timetable

Submission Deadline

Jan. 31, 2020

First notification

May 31, 2020

Final notification

July 31, 2020

Final submission

Sep. 31, 2020

Expected publication Date

Dec. 31, 2020