Yuhao Sun

Papers

Total Citations

H-Index

About

Yuhao Sun is a rising researcher in the field of neuromorphic computing and artificial intelligence, with a primary focus on recurrent spiking neural networks (RSNNs). Their work addresses a critical bottleneck in the field: while RSNNs offer immense potential for modeling complex, brain-like dynamics and advancing artificial general intelligence, they are notoriously difficult to train. Sun’s major contribution lies in pioneering novel approaches to connectivity evolution within these networks, moving beyond the limitations of standard surrogate gradient-based methods. Their most-cited paper, "Evolving Connectivity for Recurrent Spiking Neural Networks" (2023), has already garnered 3 citations, signaling early impact in this specialized area. By exploring how network topology itself can be optimized, Sun’s research paves the way for more efficient and biologically plausible learning algorithms. This work is particularly notable for its potential to unlock RSNNs for real-world applications in temporal pattern recognition and dynamic system modeling. As a young investigator, Sun is establishing a reputation for tackling fundamental challenges in neural network architecture, making them a promising voice in the next wave of neuromorphic AI research.