[DBWorld] CFP: Springer Volume on ADVANCES IN DEEP LEARNING INTEGRATIONS

Springer Volume CFP

ADVANCES IN DEEP LEARNING INTEGRATIONS: THEORY, TOOLS AND APPLICATIONS

OBJECTIVES

Artificial Intelligence, in general, and Machine Learning, in particular, are fields of very active and intense research worldwide. More specifically, the Machine Learning approach to Artificial Intelligence aims at incorporating learning abilities into machines, i.e. at developing mechanisms, methodologies, procedures and algorithms that allow machines to become better and more efficient at performing specific tasks, either on their own or with the help of a supervisor/instructor. Within the umbrella of Machine Learning, the sub-field of Deep Learning stands out due to its worldwide pace of growth in both theoretical advances and areas of applications, while achieving high rates of success and promising major impact in science, technology and society.

On the other hand, Integrated or Hybrid approaches/methods, that is approaches that combine two or more component approaches, have claimed a large part of research activities in the recent years. The aim is to create approaches that benefit from each of their components. It is generally believed that complex problems can be easier solved with such integrated or hybrid methods. Two well-known categories of such integrations are neuro-symbolic and neuro-fuzzy integrations. The first combines neural networks with symbolic approaches, like rule-based and logic-based ones, whereas the second neural networks and fuzzy logic-based ones.

However, in those integrations the neural component consisted mostly of shallow networks. Quite recently, researchers have been looking into integrations of deep neural networks (DNNs), with applications to several areas. In some cases, symbolic or fuzzy approaches are used to improve learnability of DNNs, whereas in other cases to contribute in the explainability problem of DNNs. Thus, deep learning integrations becomes a very interesting area of research.

It is expected that the proposed book on deep learning integrations: theory, tools and applications will provide a broad coverage of streamline research topics and related advances and will prove to be particularly useful to broad classes of both expert and newcomer readers.

TOPICS OF INTEREST include (but are not limited to) the following:

    Deep belief rule-based Approaches
    Deep fuzzy rule-based classifiers
    Deep fuzzy learning
    Deep neuro-symbolic approaches
    Deep neural learning and reasoning
    Deep neuro-fuzzy networks
    Deep rule-based classifiers
    Explainable deep neural networks
    Explainable deep reinforcement learning
    Informed deep learning
    Integrating deep learning with human knowledge
    Rule extraction from deep neural networks
    Other

    Applications areas
        Assistive Technologies
        Bioinformatics/Biosciences
        Computer Games
        Computer Vision
        Energy Production and Distribution and Smart Grids
        Finance
        Education & Distance Learning
        Image Processing and Understanding
        Manufacturing and Production
        Medical Diagnosis
        Natural language Processing and Understanding
        Recommendation
        Robotics
        Social Media Analytics
        Time Series Analysis and Forecasting
        Other

CHAPTER SUBMISSION

Depending on the number and themes of the selected chapters, more than one volume may arise. The intention of this book is to provide a concise coverage to the particular topic from the vantage point of a newcomer. As such, each chapter must be complete within itself. Each chapter must include an abstract, as well as a bibliography of references to additional or more advanced material. Co-authored chapters are acceptable.

At this stage follow the paper format guidelines here: https://www.springer.com/gp/computer-science/lncs/conference-proceedings-guidelines .

Please SEND your chapter proposal to the Editorial Team contact: Prof. George A. Tsihrintzis, e-mail: [email protected]
Past Series Publications

This book will constitute the seventh in a sequence of volumes on MACHINE LEARNING PARADIGMS previously published by Springer. For details on the previous six volumes, please visit:

    https://www.springer.com/gp/book/9783319191348
    https://www.springer.com/gp/book/9783319471921
    https://www.springer.com/gp/book/9783319940298
    https://www.springer.com/gp/book/9783030137427
    https://www.springer.com/gp/book/9783030497231

IMPORTANT DATES

Abstract Submission : 30 June 2021
Author Notification: 20 July 2021
Draft Chapter Submission: 20 November 2021
Feedback to authors: 31 December 2021
Final Chapter Submission: 31 January 2022
Expected Publication Date: Mid 2022

EDITORIAL TEAM

Ioannis Hatzilygeroudis
Professor
Department of Computer Engineering & Informatics
University of Patras
HELLAS (GREECE)
e-mail: [email protected]
URL: http://aigroup.ceid.upatras.gr/ihatz

George Tsihrintzis (Contact Editor)
Professor
Department of Informatics
University of Piraeus
HELLAS (GREECE)
e-mail: [email protected]
URL: http://www.unipi.gr/faculty/geoatsi/

Lakhmi C. Jain
PhD | ME | BE(Hons) | Fellow (Engineers Aust)
Professor, University of Technology Sydney, Australia
Visiting Professor, Liverpool Hope University, UK
e-mail: [email protected]
Founder KES International http://www.kesinternational.org/organisation.php
Book Depository: http://www.bookdepository.com/author/Lakhmi-Jain? 
_______________________________________________
Please do not post msgs that are not relevant to the database community at large.  Go to www.cs.wisc.edu/dbworld for guidelines and posting forms.
To unsubscribe, go to https://lists.cs.wisc.edu/mailman/listinfo/dbworld