Yukai Shi

LipsFormer: Introducing Lipschitz Continuity to Vision Transformers

2023 · arXiv (Cornell University)

We present a Lipschitz continuous Transformer, called LipsFormer, to pursue training stability both theoretically and empirically for Transformer-based models. In contrast to previous practical tricks that address training instability by learning rate warmup, layer normalization, …

Hard disk failure prediction based on improved WOA-BP

2023

In the era of rapid development of the Internet, how to ensure the Storage security of data has become an important issue. As the physical carrier of data, once the hard disk fails, it may …