activity
20202022
collaborators

5 papers

cs.LG2022

Relaxed Attention for Transformer Models

Timo Lohrenz, Björn Möller, Zhengyang Li +1

The powerful modeling capabilities of all-attention-based transformer architectures often cause overfitting and - for natural language processing tasks - lead to an implicitly lear…

math.NA2022

The Quadratic Wasserstein Metric With Squaring Scaling For Seismic Velocity Inversion

Zhengyang Li, Yijia Tang, Jing Chen +1

The quadratic Wasserstein metric has shown its power in measuring the difference between probability densities, which benefits optimization objective function with better convexity…

eess.AS2021

Multi-Encoder Learning and Stream Fusion for Transformer-Based End-to-End Automatic Speech Recognition

Timo Lohrenz, Zhengyang Li, Tim Fingscheidt

Stream fusion, also known as system combination, is a common technique in automatic speech recognition for traditional hybrid hidden Markov model approaches, yet mostly unexplored…

astro-ph.IM2020

Point Spread Function Estimation for Wide Field Small Aperture Telescopes with Deep Neural Networks and Calibration Data

Peng Jia, Xuebo Wu, Zhengyang Li +4

The point spread function (PSF) reflects states of a telescope and plays an important role in development of data processing methods, such as PSF based astrometry, photometry and i…

astro-ph.IM2020

Point Spread Function Modelling for Wide Field Small Aperture Telescopes with a Denoising Autoencoder

Peng Jia, Xiyu Li, Zhengyang Li +2

The point spread function reflects the state of an optical telescope and it is important for data post-processing methods design. For wide field small aperture telescopes, the poin…