Connectionists: CFP: Springer book on GANs

[Ariel Ruiz-Garcia]

*TL;DR – CFP:*  Springer Book on GANs
*GUEST EDITORS*:  Roozbeh Razavi-Far, Ariel Ruiz-Garcia, Vasile Palade, Jürgen
Schmidhuber

*SUBMISSION DEADLINE*: 15th April 2021


*Call for Book Chapters*



*Springer book on: *

*Generative Adversarial Learning: Architectures and Applications*



Adversarial learning has fascinated the attention of artificial
intelligence and machine learning communities across the world over the
last years. Their success is achieved by exploiting a minimax learning
concept, which has proved to be an effective paradigm in earlier works,
such as adversarial curiosity (1990) and predictability minimization
(1991), in which two networks compete in a minimax game during the learning
process. One of their key advantages over other learning methods is the
capability of generating new data from random noise, as well as their
capability to replicate data distributions. However, producing real data
using Generative Adversarial Networks (GANs) remains a challenge,
especially when particular features are required; for instance,
constraining the latent aggregate distribution space does not guarantee
that the generator will produce an image with a specific attribute.



Aside from realistic image generation, GANs have been extensively used for
numerous other application domains such as: speech and audio synthesis,
object detection and segmentation, policy learning in deep reinforcement
learning, etc., usually providing promising results. Despite their apparent
advantages and their application to a wide range of domains, GANs have yet
to overcome several challenges including model convergence, mode collapse,
vanishing gradients, model interpretability, and model sensitivity to
parameters and hyper-parameter initialization. Such problems often arise
due to the added complexity of simultaneous training of the generator and
discriminator models. Recent advancements in machine learning are expected
to provide efficient solutions to deal with the above raised challenges.



This book will provide a collection of high-quality research articles
addressing theoretical work for improving the learning process and the
generalization of GANs. State-of-the-art applications of GANs are also very
welcomed. This Springer edited book solicits contributed chapters including
but not limited to the following topics:



• Generative adversarial learning methods and theory;

• Adversarial deep learning for domain adaptation;

• Network interpretability in adversarial learning;

• Adversarial feature learning;

• Adversarial learning for data augmentation;

• Adversarial deep learning for class imbalance;

• Adversarial deep learning for semi-supervised learning;

• New GAN models and new GAN learning criteria;

• Adversarial deep learning in pattern recognition;

• GANs for noise reduction;

• GANs for imitation learning;

• GANs for image segmentation and image completion;

• GANs in deep reinforcement learning;

• GANs for image and video synthesis;

• GANs for speech and audio synthesis;

• GANs for in-painting and sketch to image;

• Adversarial learning in Neural Machine Translation;

• Object Compositionality in GANS;

• Applications of GANs in various domains, such as computer vision, cyber
security, safety, engineering, video inference, speech and emotion
recognition, voice conversion, natural language processing.



*Important Dates*



    15th March 2021 – Abstract submission deadline

    15th April 2021 – Chapter submission deadline

    30th May 2021 – Chapter acceptance notification

    31st July 2021 – Camera-ready submission deadline

    September 2021 – Book publication



*Book Editors:*



*Dr Roozbeh Razavi-Far*

University of Windsor, Canada

Email: roozbeh at uwindsor.ca



*Dr Ariel Ruiz-Garcia*

SeeChange.ai, UK

Email: ariel.9arcia at gmail.com



*Professor Vasile Palade*

Coventry University, UK

Email: vasile.palade at coventry.ac.uk



*Professor Jürgen Schmidhuber*

NNAISENSE,

Swiss AI Lab IDSIA,

USI & SUPSI, Switzerland

Email: juergen at idsia.ch



*Submission Procedure:*



Prospective authors should submit a tentative title, names and affiliation
of authors and a brief abstract with keywords of their proposed
contribution via EasyChair
<https://easychair.org/conferences/?conf=genadvlearn-book-21>. Please also
let the editors know. We strongly encourage authors to submit abstracts as
soon as possible.



Chapter submissions can be done via EasyChair
<https://easychair.org/conferences/?conf=genadvlearn-book-21>. Chapter
submissions should conform to the standard guidelines of Springer’s book
chapter format. Manuscripts must be prepared using Latex or Word according
to Springer’s author template found here
<https://www.springer.com/gp/authors-editors/book-authors-editors/your-publication-journey/manuscript-preparation>.
Submitted manuscripts will be refereed by at least two expert reviewers
following a single-blind review process. Accepted works will be published
as part of this book in the Intelligent Systems Reference Library by
Springer.



For any questions or further information please email the book editors
listed above.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20210221/36875020/attachment.html>