Overview
This editorial highlights a call for papers for a special issue in the Neural Networks journal, focusing on Generative Adversarial Networks (GANs). This opportunity is significant for researchers and practitioners in the AI and machine learning community, as it aims to gather innovative contributions that address both theoretical and practical aspects of GANs and deep representation learning.
Background & Relevance
Generative Adversarial Networks have emerged as powerful tools for data generation, utilizing a competitive learning paradigm where two networks, the generator and the discriminator, engage in a minimax game. Despite their advantages, such as the ability to generate diverse data from random noise, GANs face challenges like mode collapse and sensitivity to hyperparameter settings. The integration of deep representation learning can potentially enhance GAN performance, addressing issues like dataset bias and improving feature selection. This special issue aims to explore these advancements and their implications across various applications.
Key Details
- Submission Deadline: 30 September 2019
- First Decision Notification: 31 December 2019
- Revised Version Deadline: 28 February 2020
- Final Decision Notification: 30 April 2020
- Publication Date: July 2020
- Guest Editors:
- Dr. Ariel Ruiz-Garcia, Coventry University, UK
- Professor Jürgen Schmidhuber, NNAISENSE, Swiss AI Lab IDSIA, USI & SUPSI, Switzerland
- Dr. Vasile Palade, Coventry University, UK
- Dr. Clive Cheong Took, Royal Holloway, University of London, UK
- Professor Danilo Mandic, Imperial College London, UK
- Submission Link: Neural Networks Submission
Eligibility & Participation
This call for papers is open to researchers and practitioners who are engaged in the study and application of GANs and deep representation learning. Contributions that provide novel insights or advancements in these areas are particularly encouraged.
Submission or Application Guidelines
Prospective authors should adhere to the standard author instructions for the Neural Networks journal. Manuscripts must be submitted online through the provided link, ensuring to select “VSI:RL and GANs” during the submission process.
Additional Context / Real-World Relevance
The exploration of GANs and their integration with deep representation learning is crucial for advancing the field of machine learning. As GANs continue to find applications in diverse domains such as image processing, audio synthesis, and more, this special issue provides a platform for disseminating cutting-edge research that can drive innovation and improvements in these technologies.
Conclusion
This special issue represents a valuable opportunity for researchers to contribute to the evolving landscape of GANs and deep learning. Interested parties are encouraged to submit their work and engage with the ongoing discourse in this dynamic field. For further inquiries, please reach out to Dr. Ariel Ruiz-Garcia at ariel.9arcia@gmail.com.
Category: CFP & Deadlines
Tags: gan, generative-adversarial-networks, deep-learning, representation-learning, neural-networks, adversarial-learning, data-augmentation, machine-learning
