Despite the growing interest in continual learning, most of its contemporary works have been studied in a rather restricted setting where tasks are clearly distinguishable, and task boundaries are known during training. However, if our goal is to develop an algorithm that learns as humans do, this setting is far from realistic, and it is essential to develop a methodology that works in a task-free manner. Meanwhile, among several branches of continual learning, expansion-based methods have the advantage of eliminating catastrophic forgetting by allocating new resources to learn new data. In this work, we propose an expansion-based approach for task-free continual learning. Our model, named Continual Neural Dirichlet Process Mixture (CN-DPM), consists of a set of neural network experts that are in charge of a subset of the data. CN-DPM expands the number of experts in a principled way under the Bayesian nonparametric framework. With extensive experiments, we show that our model successfully performs task-free continual learning for both discriminative and generative tasks such as image classification and image generation.
BackgroundMetabolic syndrome is a common extrapulmonary comorbidity in patients with chronic obstructive pulmonary disease (COPD). However, the reported relationship of COPD with dyslipidemia, an important component of metabolic syndrome, is ambiguous. The aim of this meta-analysis is to investigate the association between COPD and the serum levels of high-density lipoprotein cholesterol (HDL), low-density lipoprotein cholesterol (LDL), total cholesterol (TC), and triglyceride (TG).MethodsThe PubMed and Embase databases were searched to find potential studies using the search terms of (“dyslipidemia” or “HDL” or “LDL” or “cholesterol” or “triglyceride”) and COPD. We also performed subgroup analysis enrolling patients who were not receiving treatment for dyslipidemia. Mean differences (MD) with 95% confidence intervals (CI) were estimated with random effects models.ResultsA total of 11 studies comprising 615 cases and 471 controls were included in the study. No significant differences were found in the HDL (MD = −2.55, 95% CI [−6.03, 0.93], P = 0.15), LDL (MD = −2.25, 95% CI [−13.36, 8.86], P = 0.69), TC (MD = −2.69, 95% CI [−13.30, 7.92], P = 0.62), and TG (MD = 6.90, 95% CI [−2.81, 16.60], P = 0.16) levels of the 2 groups. However, subgroup analysis enrolling patients who were not receiving treatment for dyslipidemia showed that TG levels were higher in patients with stable COPD than in healthy individuals (MD = 16.35, 95% CI [5.90, 26.80], P = 0.002).ConclusionsExcluding the impact of hypolipidemic treatment on serum lipid profile, TG levels were higher in patients with COPD than in healthy individuals. This meta-analysis suggested that physicians should screen COPD patients for elevated TG levels to reduce the risk of cardiovascular morbidity and mortality.
We propose spatial semantic embedding network (SSEN), a simple, yet efficient algorithm for 3D instance segmentation using deep metric learning. The raw 3D reconstruction of an indoor environment suffers from occlusions, noise, and is produced without any meaningful distinction between individual entities. For high-level intelligent tasks from a large scale scene, 3D instance segmentation recognizes individual instances of objects. We approach the instance segmentation by simply learning the correct embedding space that maps individual instances of objects into distinct clusters that reflect both spatial and semantic information. Unlike previous approaches that require complex pre-processing or post-processing, our implementation is compact and fast with competitive performance, maintaining scalability on large scenes with high resolution voxels. We demonstrate the state-of-the-art performance of our algorithm in the ScanNet 3D instance segmentation benchmark on AP score. 1
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.