Learning efficient convolutional networks through network slimming
The deployment of deep convolutional neural networks (CNNs) in many real world applications
is largely hindered by their high computational cost. In this paper, we propose a novel …
is largely hindered by their high computational cost. In this paper, we propose a novel …
Mechanical properties and deformation mechanisms of gradient nanostructured metals and alloys
Inspired by the gradient structures of biological materials, researchers have explored
compositional and structural gradients for about 40 years as an approach to enhance the …
compositional and structural gradients for about 40 years as an approach to enhance the …
[HTML][HTML] Scalable aesthetic transparent wood for energy efficient buildings
Nowadays, energy-saving building materials are important for reducing indoor energy
consumption by enabling better thermal insulation, promoting effective sunlight harvesting and …
consumption by enabling better thermal insulation, promoting effective sunlight harvesting and …
Boosting adversarial attacks with momentum
Deep neural networks are vulnerable to adversarial examples, which poses security concerns
on these algorithms due to the potentially severe consequences. Adversarial attacks …
on these algorithms due to the potentially severe consequences. Adversarial attacks …
A strong, biodegradable and recyclable lignocellulosic bioplastic
Renewable and biodegradable materials derived from biomass are attractive candidates to
replace non-biodegradable petrochemical plastics. However, the mechanical performance …
replace non-biodegradable petrochemical plastics. However, the mechanical performance …
Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting
Accurate prediction of the future given the past based on time series data is of paramount
importance, since it opens the door for decision making and risk management ahead of time. In …
importance, since it opens the door for decision making and risk management ahead of time. In …
Dsod: Learning deeply supervised object detectors from scratch
We present Deeply Supervised Object Detector (DSOD), a framework that can learn object
detectors from scratch. State-of-the-art object objectors rely heavily on the off-the-shelf …
detectors from scratch. State-of-the-art object objectors rely heavily on the off-the-shelf …
Clinical features and short-term outcomes of 221 patients with COVID-19 in Wuhan, China
G Zhang, C Hu, L Luo, F Fang, Y Chen, J Li… - Journal of Clinical …, 2020 - Elsevier
Background In late December 2019, an outbreak of acute respiratory illness, coronavirus
disease 2019 (COVID-19), emerged in Wuhan, China. We aimed to study the epidemiology, …
disease 2019 (COVID-19), emerged in Wuhan, China. We aimed to study the epidemiology, …
[HTML][HTML] Membrane active antimicrobial peptides: translating mechanistic insights to design
J Li, JJ Koh, S Liu, R Lakshminarayanan… - Frontiers in …, 2017 - frontiersin.org
Antimicrobial peptides (AMPs) are promising next generation antibiotics that hold great
potential for combating bacterial resistance. AMPs can be both bacteriostatic and bactericidal, …
potential for combating bacterial resistance. AMPs can be both bacteriostatic and bactericidal, …
Chronic intermittent hypoxia induces atherosclerosis
V Savransky, A Nanayakkara, J Li… - American journal of …, 2007 - atsjournals.org
Rationale: Obstructive sleep apnea, a condition leading to chronic intermittent hypoxia (CIH),
is associated with hyperlipidemia, atherosclerosis, and a high cardiovascular risk. A causal …
is associated with hyperlipidemia, atherosclerosis, and a high cardiovascular risk. A causal …