Xinliang Wu
Papers
1
Total Citations
4
H-Index
1
About
Xinliang Wu is a researcher focused on advancing deep learning architectures, particularly in the comparative analysis of convolutional neural networks (CNNs) and emerging models like CapsuleNet. His most-cited work, "The Analysis Between Traditional Convolution Neural Network and CapsuleNet" (2018), critically examines the strengths and limitations of CNNs—widely used in autonomous driving, robotics, and medical imaging—while exploring CapsuleNet’s potential to overcome challenges such as spatial hierarchy and viewpoint invariance. This study has garnered 4 citations, reflecting its foundational role in guiding researchers toward more robust neural network designs. Wu’s contributions lie in demystifying complex network structures and highlighting practical trade-offs for real-world applications. By bridging theoretical insights with applied domains, his work supports the development of safer autonomous systems and more accurate diagnostic tools. For students and researchers navigating the evolving landscape of deep learning, Wu’s analysis offers a clear, comparative lens that informs both current practice and future innovation in neural network research.
Research Focus
Key Achievements
Top Papers
- 1