Weikang Tang
Papers
1
Total Citations
4
H-Index
1
About
Weikang Tang has made significant contributions to the field of deep learning, with a particular focus on advancing the architecture and understanding of neural networks. His most cited work, "The Analysis Between Traditional Convolution Neural Network and CapsuleNet" (2018), provides a critical comparative study that has garnered 4 citations, offering valuable insights into the strengths and limitations of CNNs versus emerging CapsuleNet models. This research is especially relevant to applications in autonomous driving, robotics, and medical imaging, where CNNs have achieved breakthroughs. Tang’s analysis helps clarify how alternative architectures might overcome traditional CNN shortcomings, such as spatial hierarchy understanding. His work demonstrates a keen ability to dissect complex neural network designs, making him a thoughtful contributor to the ongoing evolution of machine learning. By bridging theoretical comparison with practical implications, Tang’s research serves as a useful guide for students and engineers navigating the rapidly advancing landscape of deep learning architectures.
Research Focus
Key Achievements
Top Papers
- 1