Sanghyuk Kim
Papers
1
Total Citations
20
H-Index
1
About
Sanghyuk Kim is a researcher whose work sits at the intersection of optimization algorithms and artificial neural networks, with a particular focus on improving the efficiency and performance of machine learning models. His most-cited contribution, the 2022 paper "Variable three-term conjugate gradient method for training artificial neural networks," introduces a novel optimization technique that enhances the training process of neural networks. This work has already garnered 20 citations, reflecting its growing influence in the field of computational intelligence. By developing a variable three-term conjugate gradient method, Kim addresses key challenges in training deep learning models, such as slow convergence and high computational costs, offering a more robust and adaptive alternative to traditional gradient-based methods. His research is particularly valuable for students and researchers working on neural network optimization, as it provides practical tools for accelerating model training while maintaining accuracy. Kim's contributions highlight his expertise in bridging theoretical optimization with real-world machine learning applications, making him a notable figure in the ongoing effort to refine AI training methodologies.
Research Focus
Key Achievements
Top Papers
- 1