Improving Robustness of Deep Convolutional Neural Networks via Multiresolution Learning

no code implementations • 24 Sep 2023 • Hongyan Zhou, Yao Liang

The current learning process of deep learning, regardless of any deep neural network (DNN) architecture and/or learning algorithm used, is essentially a single resolution training.

Adversarial Robustness

Monolithic Integrated Multiband Acoustic Devices on Heterogeneous Substrate for Sub-6 GHz RF-FEMs

no code implementations • 20 Oct 2021 • Shibin Zhang, Hongyan Zhou, Pengcheng Zheng, Jinbo Wu, Liping Zhang, Zhongxu Li, Kai Huang, Xin Ou, Xi Wang

Monolithic integration of multiband (1. 4~ 6. 0 GHz) RF acoustic devices were successfully demonstrated within the same process flow by using the lithium niobate (LN) thin film on silicon carbide (LNOSiC) substrate.

Model Adaptation via Model Interpolation and Boosting for Web Search Ranking

no code implementations • 22 Jul 2019 • Jianfeng Gao, Qiang Wu, Chris Burges, Krysta Svore, Yi Su, Nazan Khan, Shalin Shah, Hongyan Zhou

This paper explores two classes of model adaptation methods for Web search ranking: Model Interpolation and error-driven learning approaches based on a boosting algorithm.