Collection
Graph Theory-based Approaches for Optimizing Neural Network Architectures
This special issue aims at bringing together articles that discuss recent advances in Graph Theory-based Approaches for Optimizing Neural Network Architectures. Graph theory has emerged as a powerful tool for optimizing neural network architectures. As the field of artificial intelligence continues to advance, researchers and engineers look for innovative methods to design more efficient and effective neural networks. Exploiting graph theory principles can address challenges related to model complexity, training efficiency and generalization capabilities. In Neural networks, especially deep learning models have demonstrated remarkable success in various tasks such as image recognition, natural language processing and speech synthesis. However, the increased complexity of these models comes with a trade-off. Graph theory provides a framework for modeling neural networks as graphs provided with neurons as nodes and connections as edges. We encourage submissions from researchers in this background to demonstrate the effectiveness of graph theory-based approaches on various benchmark datasets and real-world applications.
Editors
-
Dr. Jia-Bao Liu
Anhui Jianzhu University, China
-
Dr. Muhammad Javaid
University of Management and Technology, Pakistan
-
Dr. Mohammad Reza Farahani
Iran University of Science and Technology
