SCOPE

In the last years, inspired by the fact that natural brains themselves are the products of an evolutionary process, the quest for evolving and optimizing artificial neural networks through evolutionary computation has enabled researchers to successfully apply neuroevolution to many domains such as strategy games, robotics, big data, and so on. The reason behind this success lies in important capabilities that are typically unavailable to traditional approaches, including evolving neural network building blocks, hyperparameters, architectures and even the algorithms for learning themselves (meta-learning).

Although promising, the use of neuroevolution poses important problems and challenges for its future developments. Firstly, many of its paradigms suffer from lack of parameter-space diversity, meaning with this a failure in providing diversity in the behaviors generated by the different networks. Moreover, the harnessing of neuroevolution to optimize deep neural networks requires noticeable computational power and, consequently, the investigation of new trends in enhancing the computational performance.

NEWK@Work workshop aims:

- to bring together researchers working in the fields of deep learning, evolutionary computation and optimization to exchange new ideas about potential directions for future research;

- to create a forum of excellence on neuroevolution that will help interested researchers from a variety of different areas, ranging from computer scientists and engineers on the one hand to application-devoted researchers on the other hand, to gain a high-level view about the current state of the art.

Since an increasing trend to neuroevolution in the next years seems likely to be observed, not only will a workshop on this topic be of immediate relevance to get an insight in future trends, it will also provide a common ground to encourage novel paradigms and applications. Therefore, researchers putting emphasis on neuroevolution issues in their work are encouraged to submit their work. This event is also the ideal place for informal contacts, exchanges of ideas and discussions with fellow researchers.

TOPICS

The scope of the workshop is to receive high-quality contributions on topics related to neuroevolution, ranging from theoretical works to innovative applications in the context of (but not limited to):

• theoretical and experimental studies involving neuroevolution on machine learning in general, and on deep and reinforcement learning in particular
• development of innovative neuroevolution paradigms
• parallel and distributed neuroevolution methods
• new search operators for neuroevolution
• hybrid methods for neuroevolution
• surrogate models for fitness estimation in neuroevolution
• applications of neuroevolution to Artificial Intelligence agents and to real-world problems and games

Submission and important dates

Submission opening: TBA

Paper Submission deadline: April 12, 2021
Notification of paper acceptance: April 26, 2021 
Camera ready submission: May 3, 2021
Author registration deadline: TBA
Conference dates: July 10th-14th, 2021

General information on GECCO workshops can be found at
http://gecco-2021.sigevo.org/Workshops

SUBMISSION GUIDELINES

Authors must submit their papers using the GECCO submission site at
https://ssl.linklings.net/conferences/gecco.
Submissions should adhere to the ACM SIG guidelines as GECCO’s full papers:
Papers Submission Instructions.

Each paper submitted will be rigorously evaluated in a double-blind review process. The evaluation will ensure high interest and expertise of the reviewers. Review criteria include significance of the work, technical soundness, novelty, clarity, writing quality, and sufficiency of information to permit replication, if applicable. All accepted papers will be published in the ACM Digital Library.

Program Committee

Andrés Camero Unzueta, University of Malaga, Spain
Anders Lyhne Christensen, University of Southern Denmark, Denmark
Paulo Cortez, University of Minho, Portugal
Victor Costa, University of Coimbra, Portugal
Federico Divina, Pablo de Olavide University, Spain
Marcio Dorn, Federal University of Rio Grande do Sul, Brazil
Jacqueline Fairley, Georgia Tech Research Institute, USA
Steffen Finck, FH Vorarlberg University of Applied Sciences, Austria
Seyed Mohammad J. Jalali, Deakin University, Australia
Colin Johnson, University of Nottingham, UK
Steven Künzel, Universität der Bundeswehr München, Germany
Jacek Mańdziuk, Warsaw University of Technology, Poland
Karl Mason, University of Ireland Galway, Ireland
Risto Miikkulainen, The University of Texas, USA
Yukai Qiao, University of Queensland, Australia
Catherine D. Schuman, University of Tennesse, USA
Lukas Sekanina, Brno University of Technology, Czech Republic
Thomas Stibor, GSI Helmholtz Centre for Heavy Ion Research, Germany
Jörg Stork, TH Köln, Germany
Renato Tinós, University of São Paulo, Brazil
Liqiang Wang, University of Central Florida, USA

GECCO'21 goes online

GECCO 2021 will be an electronic-only conference due to COVID-19. It will be required that the presentation of all accepted papers is provided in the form of a pre-recorded talk. More details about this will be provided soon together with how workshop discussions will occur.

Journal Special Issue

Authors of selected papers will be invited to submit an extended version on a Special Issue  entitled "Evolutionary Machine Learning" published in "The Knowledge Engineering Review” journal, Cambridge University Press.

https://www.cambridge.org/core/news/evolutionary-machine-learning

Organized by


Ivanoe De Falco
ICAR-CNR, ITALY

Antonio Della Cioppa
University of Salerno, ITALY

Ernesto Tarantino
ICAR-CNR, ITALY

Umberto Scafuri
ICAR-CNR, ITALY

gecco2021_logologo sigevo_new-332acm_logo