Neural Networks

Top Research Topics at Neural Networks?

Neural Networks is organized to address concerns in the fields of Artificial neural network, Artificial intelligence, Algorithm, Pattern recognition and Machine learning. The concepts on Artificial neural network presented in Neural Networks can also apply to other research fields, including Applied mathematics and Control theory, Nonlinear system. Synchronization (computer science) and Synchronization are some topics wherein Control theory research discussed in the journal have an impact.

The Artificial intelligence study tackled is a key component of adjacent topics in the area of Computer vision. Neural Networks covers various topics on Pattern recognition such as Convolutional neural network and Classifier (UML).

• Artificial neural network (52.17%)
• Artificial intelligence (51.38%)
• Algorithm (17.47%)

What are the most cited papers published in the journal?

• Multilayer feedforward networks are universal approximators (11582 citations)
• Multilayer feedforward networks are universal approximators (9637 citations)
• Deep learning in neural networks (9343 citations)

Research areas of the most cited articles at Neural Networks:

The most cited papers focus on Artificial neural network, Artificial intelligence, Algorithm, Control theory and Machine learning. While the primary focus in the most cited articles is Artificial neural network, they also dissect topics surrounding Exponential stability and Equilibrium point as a whole. The journal publications with studies in Artificial intelligence featured incorporate elements of Computer vision and Pattern recognition.

What topics the last edition of the journal is best known for?

• Artificial intelligence
• Machine learning
• Quantum mechanics

The previous edition focused in particular on these issues:

Neural Networks primarily focuses on research topics in Artificial intelligence, Artificial neural network, Deep learning, Pattern recognition and Machine learning. Convolutional neural network, Feature (computer vision), Benchmark (computing), Recurrent neural network and Contextual image classification are all topics related to Artificial intelligence research discussed. In addition to Artificial neural network research, the journal aims to explore topics under Stability (learning theory), Control theory, Applied mathematics, Function (mathematics) and Algorithm.

The study on Control theory presented in Neural Networks intersects with the topics under Synchronization (computer science). Neural Networks explores topics in Deep learning which can be helpful for research in disciplines like Feature extraction and Speech recognition. The Pattern recognition study featured in it draws connections with the study of Cluster analysis.

The most cited articles from the last journal are:

• FPGAN: Face de-identification method with generative adversarial networks for social robots. (28 citations)
• Fast convergence rates of deep neural networks for classification. (18 citations)
• Neural network approximation: Three hidden layers are enough. (18 citations)

Papers citation over time

A key indicator for each journal is its effectiveness in reaching other researchers with the papers published at that venue.

The chart below presents the interquartile range (first quartile 25%, median 50% and third quartile 75%) of the number of citations of articles over time.

Top authors and change over time

The top authors publishing in Neural Networks (based on the number of publications) are:

• Stephen Grossberg (78 papers) absent at the last edition,
• Jinde Cao (76 papers) published 7 papers at the last edition, 2 more than at the previous edition,
• Tingwen Huang (52 papers) published 3 papers at the last edition, 7 less than at the previous edition,
• John G. Taylor (46 papers) absent at the last edition,
• Zhigang Zeng (43 papers) published 5 papers at the last edition, 2 less than at the previous edition.

The overall trend for top authors publishing in this journal is outlined below. The chart shows the number of publications at each edition of the journal for top authors.

Top affiliations and change over time

Only papers with recognized affiliations are considered

The top affiliations publishing in Neural Networks (based on the number of publications) are:

• Boston University (121 papers) absent at the last edition,
• Southeast University (94 papers) published 13 papers at the last edition, 3 more than at the previous edition,
• Chinese Academy of Sciences (85 papers) published 15 papers at the last edition, 1 less than at the previous edition,
• University of Tokyo (76 papers) published 7 papers at the last edition the same number as at the previous edition,
• City University of Hong Kong (60 papers) published 6 papers at the last edition the same number as at the previous edition.

The overall trend for top affiliations publishing in this journal is outlined below. The chart shows the number of publications at each edition of the journal for top affiliations.

Publication chance based on affiliation

The publication chance index shows the ratio of articles published by the best research institutions in the journal edition to all articles published within that journal. The best research institutions were selected based on the largest number of articles published during all editions of the journal.

The chart below presents the percentage ratio of articles from top institutions (based on their ranking of total papers).Top affiliations were grouped by their rank into the following tiers: top 1-10, top 11-20, top 21-50, and top 51+. Only articles with a recognized affiliation are considered.

During the most recent 2021 edition, 2.09% of publications had an unrecognized affiliation. Out of the publications with recognized affiliations, 15.73% were posted by at least one author from the top 10 institutions publishing in the journal. Another 11.47% included authors affiliated with research institutions from the top 11-20 affiliations. Institutions from the 21-50 range included 16.27% of all publications and 56.53% were from other institutions.

Returning Authors Index

A very common phenomenon observed among researchers publishing scientific articles is the intentional selection of journals they have already attended in the past. In particular, it is worth analyzing the case when the authors participate in the same journal from year to year.

The Returning Authors Index presented below illustrates the ratio of authors who participated in both a given as well as the previous edition of the journal in relation to all participants in a given year.

Returning Institution Index

The graph below shows the Returning Institution Index, illustrating the ratio of institutions that participated in both a given and the previous edition of the conference in relation to all affiliations present in a given year.

The experience to innovation index

Our experience to innovation index was created to show a cross-section of the experience level of authors publishing in a journal. The index includes the authors publishing at the last edition of a journal, grouped by total number of publications throughout their academic career (P) and the total number of citations of these publications ever received (C).

The group intervals were selected empirically to best show the diversity of the authors' experiences, their labels were selected as a convenience, not as judgment. The authors were divided into the following groups:

• Novice - P < 5 or C < 25 (the number of publications less than 5 or the number of citations less than 25),
• Competent - P < 10 or C < 100 (the number of publications less than 10 or the number of citations less than 100),
• Experienced - P < 25 or C < 625 (the number of publications less than 25 or the number of citations less than 625),
• Master - P < 50 or C < 2500 (the number of publications less than 50 or the number of citations less than 2500),
• Star - P ≥ 50 and C ≥ 2500 (both the number of publications greater than 50 and the number of citations greater than 2500).

The chart below illustrates experience levels of first authors in cases of publications with multiple authors.

Real-World Applications of Neural Networks

Another essential perspective to the subject of Neural Networks is understanding their real-world applications. Seeing how the theories and algorithms are put into practice helps to ground the academic research conducted in the field. One significant area where Neural Networks are increasing being applied is in the domain of Education. The learning algorithms of Neural Networks are being used to personalize and enhance the teaching process. They help analyze patterns in the learner's behavior and adapt the teaching approach and materials effectively. A noteworthy example of application of Neural Networks is the creation of intelligent systems designed for education purposes. For instance, there are systems in place that can guide aspiring teachers on best practices and steps towards achieving their career goals. If you're interested in this area, you can learn more about it by viewing this guide on how to become a high school art teacher in Mississippi. Another popular application is in the field of Computer Vision. Neural networks have become a standard tool for image analysis, helping develop more precise facial recognition systems, self-driving cars, medical diagnosis tools, and more. These examples of real-world applications illustrate the range of potential uses for neural networks, further underlining how important it is to continue research in this field.