Neural Networks Journal

About | Subscriptions | Submissions | Open Access | Best Paper Award | Contact

About Neural Networks

Neural Networks is the archival journal of the world's three oldest neural modeling societies: the International Neural Network Society, the European Neural Network Society, and the Japanese Neural Network Society.

Neural Networks provides a forum for developing and nurturing an international community of scholars and practitioners who are interested in all aspects of neural networks and related approaches to computational intelligence. Neural Networks welcomes high-quality submissions that contribute to the full range of neural networks research, from behavioral and brain modeling, learning algorithms, through mathematical and computational analyses, to engineering and technological applications of systems that significantly use neural network concepts and techniques.

This uniquely broad range facilitates the cross-fertilization of ideas between biological and technological studies, and helps to foster the development of the interdisciplinary community that is interested in biologically-inspired computational intelligence. Accordingly, the Neural Networks Editorial Board represents experts in fields including psychology, neurobiology, computer science, engineering, mathematics, and physics.

The journal publishes articles, letters, reviews, and current opinions, as well as letters to the editor, book reviews, editorials, current events, software surveys, and patent information. Articles are published in one of five sections: Cognitive Science, Neuroscience, Learning Systems, Mathematical and Computational Analysis, Engineering and Applications.

Subscriptions

The journal is published twelve times a year. Neural Networks can be accessed electronically via Science Direct, which is used by over eight million individuals worldwide.

All INNS members receive an online subscription to Neural Networks. To activate your online access, please click this link. You will need your INNS member number.

Neural Networks is now available via ContentsDirect, Elsevier Science's FREE online, e-mail alerting service. Approximately 2-4 weeks prior to each issue's publication you will receive the issue's table of contents - directly to your desktop. Register for this service here.

Submissions

Contributions to Neural Networks can now be submitted electronically by using the Elsevier EES system.

Instructions to authors can be found here.

Open Access

Neural Networks Journal has a publication fee (Article Publishing Charge, APC), which needs to be met by the authors, or their institution or funders, for each article published open access. This ensures your article will be immediately and permanently free to access by everyone.

The Article Publishing Charge for Neural Networks is USD 3350, excluding taxes.

INNS members can receive additional support with a further 25% contribution from INNS towards their open access article processing charges for accepted papers. If you are an INNS member, please submit this web form to receive reimbursement for 25% of your open access article processing charges. You will be asked to submit a PDF copy of your acceptance and production email, as well as a Wire Transfer Form.

Best Paper Award - Recipient Announcement

We are pleased to announce the 2024 Best Paper Award, “Discovering parametric activation functions” by Garrett Bingham and Risto Miikkulainen.

This paper is published in Neural Networks, volume 148, pp. 48-65, April 2022. The paper can be accessed here. The Neural Networks Best Paper Award recognizes a single outstanding paper published in Neural Networks annually. The Award carries an award plaque and a $2000 honorarium, to be split equally among the co-authors of the selected paper. No self-nomination is allowed, and no paper authored or co-authored by a Co-Editor-in-Chief is eligible for the Award.

This Award will be presented at the 2025 International Joint Conference on Neural Networks (IJCNN), during June 30 – July 5, in Rome,Italy.

Nomination Process:

To submit a nomination for the Neural Networks Best Paper Award, the materials needed are the following:

Nomination Letter with the following information:

o Nominator: name, affiliation, and email address of nominator.

o Nominated Paper: full citation of the paper, authors and their affiliations, postal addresses and email addresses.

o Basis for Nomination: detailed documentation to justify the overall quality and impact of the paper (no more than 2 pages).

• Nominated paper in PDF format. The complete nomination packet must be saved in a single PDF file containing the above information in the given order. The name of the file must be surname_of_the_first_authorNN.pdf. The complete nomination packet must be submitted by email to a Co-Editor-in-Chief. Only when the Co-EIC acknowledges receipt of the nomination packet, the submission procedure can be considered complete.

The past Best Paper awardees are:

Suogui Dang, Yining Wu, Rui Yan, and Huajin Tang: "Why grid cells function as a metric for space," Neural Networks, volume 142, pp. 128-137, October 2021.
Guan’an Wang, Yang Yang, Tianzhu Zhang, Jian Cheng, Zengguang Hou, Prayag Tiwari, and Hari Mohan Pandey: "Cross-modality paired-images generation and augmentation for RGB-infrared person re-identification," Neural Networks, volume 128, pp 294-304, August 2020.
German Parisi, Ronald Kemker, Jose Part, Christopher Kanan, and Stefan Wermter: “Continual lifelong learning with neural networks: A review,” Neural Networks, volume 113, pp. 54-71, May 2019.
Xiao-Lei Zhang: "Multilayer bootstrap networks," Neural Networks, volume 103, pp. 29-43, July 2018.
Steven Grossberg: "Towards solving the hard problem of consciousness: The varieties of brain resonances and the conscious experiences that they support," Neural Networks, volume 87, pp. 38-95, March 2017.
Nikola Kasabov et al.: "Evolving Spatio-temporal Data Machines Based on the NeuCube Neuromorphic Framework: Design Methodology and Selected Applications," Neural Networks, volume 78, pp. 1-14, June 2016.
Jürgen Schmidhuber: "Deep Learning in Neural Networks: An Overview," Neural Networks, volume 61, pp. 85-117, January 2015.