Výsledky vyhledávání - "Zhu, Michelle"

Report

Conversion and Implementation of State-of-the-Art Deep Learning Algorithms for the Classification of Diabetic Retinopathy

Autor: Rao, Mihir, Zhu, Michelle, Wang, Tianyang

Diabetic retinopathy (DR) is a retinal microvascular condition that emerges in diabetic patients. DR will continue to be a leading cause of blindness worldwide, with a predicted 191.0 million globally diagnosed patients in 2030. Microaneurysms, hemor

Externí odkaz: http://arxiv.org/abs/2010.11692

Zobrazit plný text záznamu

Akademický článek

On multi-path bandwidth scheduling for multiple fixed-slot reservations in high-performance networks

Autor: Huo, Kaitao, Wang, Yongqiang, Ji, Chen, Yue, Chen, Wu, Chase Q., Zhu, Michelle M.

Publikováno v: In Computer Communications 1 December 2023 212:63-77

Zobrazit plný text záznamu

Report

Instance-based Deep Transfer Learning

Autor: Wang, Tianyang, Huan, Jun, Zhu, Michelle

Deep transfer learning recently has acquired significant research interest. It makes use of pre-trained models that are learned from a source domain, and utilizes these models for the tasks in a target domain. Model-based deep transfer learning is pr

Externí odkaz: http://arxiv.org/abs/1809.02776

Zobrazit plný text záznamu

Report

An ELU Network with Total Variation for Image Denoising

Autor: Wang, Tianyang, Qin, Zhengrui, Zhu, Michelle

In this paper, we propose a novel convolutional neural network (CNN) for image denoising, which uses exponential linear unit (ELU) as the activation function. We investigate the suitability by analyzing ELU's connection with trainable nonlinear react

Externí odkaz: http://arxiv.org/abs/1708.04317

Zobrazit plný text záznamu