Xinyi Tang
Papers
1
Total Citations
2
H-Index
1
About
Xinyi Tang is a rising researcher in brain-inspired computing, focusing on the intersection of spiking neural networks (SNNs) and context-dependent learning. Their most-cited work, "Effect Exploration of the Spiking Neuron Property and Heterogeneity on Brain-Inspired Context-Dependent Learning" (2023), investigates how the unique properties and heterogeneity of spiking neurons can enhance the ability of SNNs to process unstructured information in real time—a critical step toward artificial general intelligence. By exploring how neural variability influences learning dynamics, Tang’s research sheds light on designing more adaptive and efficient brain-inspired models. Though early in their career, with 2 citations on this key paper, their work contributes to a foundational understanding of SNN architectures that mimic the human brain’s information processing. Tang’s research holds promise for advancing real-time, context-aware computing systems, bridging neuroscience and artificial intelligence. Their focus on neuron heterogeneity offers a novel perspective for overcoming limitations in traditional neural networks, positioning them as a thoughtful contributor to the evolving field of neuromorphic computing.
Research Focus
Key Achievements
Top Papers
- 1