Neural Networks - Elsevier - Impact Factor

Neural Networks - Elsevier | 2025 Impact Factor:7.2 | Cite Score:10.9 | SCOPUS Q1

Impact Factor and Journal Rank of Neural Networks

About: Neural Networks is a highly respected, peer-reviewed academic journal that publishes significant research in the field of artificial neural networks and related areas. It is the official journal of the International Neural Network Society (INNS) and the European Neural Network Society (ENNS), and it is published by Elsevier. The journal serves as a comprehensive platform for the dissemination of the latest advancements, theoretical insights, and practical applications of neural networks and related artificial intelligence (AI) technologies.
Content: Original Research Articles: Detailed reports presenting new research findings, innovative methodologies, and significant advances in neural network theory and application. Comprehensive reviews that summarize and synthesize existing research, providing a broad overview of specific areas within the field and identifying future research directions. Shorter articles that focus on novel techniques, preliminary findings, or innovative ideas that contribute to the development of neural networks.
High Standards and Impact: The journal maintains rigorous standards of quality through a thorough peer-review process conducted by experts in the field. It is recognized for its high impact and influence, with articles frequently cited by researchers and practitioners.
Global Reach: Neural Networks attracts contributions from a diverse group of researchers and institutions worldwide, ensuring a wide range of perspectives, methodologies, and applications.
Significance: It is a leading academic journal that significantly contributes to the advancement of research and application in the field of neural networks. Its broad scope, high standards, and global reach make it an indispensable resource for researchers, practitioners, and educators interested in the dynamic and rapidly evolving field of artificial neural networks and related AI technologies.

Journal Home: Journal Homepage

Editor-in-Chief: DeLiang Wang

Scope: The journal Neural Networks publishes a wide range of articles that contribute to the field of neural networks and related topics in artificial intelligence, machine learning, and computational neuroscience.
The scope of the journal includes, but is not limited to, the following areas:
Artificial Neural Networks (ANNs): Research on the development, analysis, and application of artificial neural networks, including feedforward, recurrent, convolutional, and other network architectures.
Deep Learning: Advances in deep learning methodologies, architectures, training techniques, and their applications in various domains such as image recognition, natural language processing, and reinforcement learning.
Biologically Inspired Neural Networks: Studies that draw inspiration from biological neural systems to design and analyze artificial neural networks, including spiking neural networks and neuromorphic computing.
Learning Algorithms: Development and improvement of learning algorithms for neural networks, including supervised, unsupervised, semi-supervised, and reinforcement learning.
Theoretical Foundations: Research on the theoretical aspects of neural networks, including learning theory, stability analysis, convergence properties, and computational complexity.
Neural Network Applications: Practical applications of neural networks in diverse fields such as robotics, healthcare, finance, cybersecurity, and autonomous systems.
Neural Network Models and Architectures: Design and evaluation of various neural network models and architectures tailored for specific tasks or performance improvements.
Cognitive and Behavioral Neuroscience: Interdisciplinary research connecting neural network models with cognitive science and behavioral neuroscience to understand and replicate human cognition and behavior.