Voxelwise detection of cerebral microbleed in CADASIL patients by leaky rectified linear unit and early stopping

2017 ◽  
Vol 77 (17) ◽  
pp. 21825-21845 ◽  
Author(s):  
Yu-Dong Zhang ◽  
Xiao-Xia Hou ◽  
Yi Chen ◽  
Hong Chen ◽  
Ming Yang ◽  
...  
Keyword(s):  
Early Stopping ◽  
Cerebral Microbleed ◽  
Rectified Linear Unit ◽  
Leaky Rectified Linear Unit

Deep extreme learning machine with leaky rectified linear unit for multiclass classification of pathological brain images

2019 ◽  
Vol 79 (21-22) ◽  
pp. 15381-15396 ◽  
Author(s):  
Deepak Ranjan Nayak ◽  
Dibyasundar Das ◽  
Ratnakar Dash ◽  
Snehashis Majhi ◽  
Banshidhar Majhi
Keyword(s):  
Extreme Learning Machine ◽  
Multiclass Classification ◽  
Brain Images ◽  
Rectified Linear Unit ◽  
Learning Machine ◽  
Leaky Rectified Linear Unit

Maxout Networks for Visual Recognition

2019 ◽  
Vol 10 (4) ◽  
pp. 1-25
Author(s):  
Gabriel Castaneda ◽  
Paul Morris ◽  
Taghi M Khoshgoftaar
Keyword(s):  
Neural Networks ◽  
Visual Recognition ◽  
Activation Function ◽  
Entity Recognition ◽  
Activation Functions ◽  
Hyperbolic Tangent ◽  
Rectified Linear Unit ◽  
Facial Identification ◽  
Leaky Rectified Linear Unit ◽  
Better Than

This study investigates the effectiveness of multiple maxout activation variants on image classification, facial identification and verification tasks using convolutional neural networks. A network with maxout activation has a higher number of trainable parameters compared to networks with traditional activation functions. However, it is not clear if the activation function itself or the increase in the number of trainable parameters is responsible for yielding the best performance on different entity recognition tasks. This article investigates if an increase in the number of convolutional filters on the rectified linear unit activation performs equal-to or better-than maxout networks. Our experiments compare rectified linear unit, leaky rectified linear unit, scaled exponential linear unit, and hyperbolic tangent to four maxout variants. Throughout the experiments, we found that on average, across all datasets, the rectified linear unit networks perform better than any maxout activation when the number of convolutional filters is increased six times.

scholarly journals Cardiovascular consequences of discontinuing low-dose rivaroxaban in people with chronic coronary or peripheral artery disease

Heart ◽  
2021 ◽  
pp. heartjnl-2020-318758
Author(s):  
Gilles R Dagenais ◽  
Leanne Dyal ◽  
Jacqueline J Bosch ◽  
Darryl P Leong ◽  
Victor Aboyans ◽  
...  
Keyword(s):  
Peripheral Artery Disease ◽  
Low Dose ◽  
Cardiovascular Death ◽  
Stroke Rate ◽  
Early Stopping ◽  
Peripheral Artery ◽  
Once Daily ◽  
Registration Number ◽  
Artery Disease

ObjectiveIn patients with chronic coronary or peripheral artery disease enrolled in the Cardiovascular Outcomes for People Using Anticoagulation Strategies trial, randomised antithrombotic treatments were stopped after a median follow-up of 23 months because of benefits of the combination of rivaroxaban 2.5 mg two times per day and aspirin 100 mg once daily compared with aspirin 100 mg once daily. We assessed the effect of switching to non-study aspirin at the time of early stopping.MethodsIncident composite of myocardial infarction, stroke or cardiovascular death was estimated per 100 person-years (py) during randomised treatment (n=18 278) and after study treatment discontinuation to non-study aspirin (n=14 068).ResultsDuring randomised treatment, the combination compared with aspirin reduced the composite (2.2 vs 2.9/100 py, HR: 0.76, 95% CI 0.66 to 0.86), stroke (0.5 vs 0.8/100 py, HR: 0.58, 95% CI 0.44 to 0.76) and cardiovascular death (0.9 vs 1.2/100 py, HR: 0.78, 95% CI 0.64 to 0.96). During 1.02 years after early stopping, participants originally randomised to the combination compared with those randomised to aspirin had similar rates of the composite (2.1 vs 2.0/100 py, HR: 1.08, 95% CI 0.84 to 1.39) and cardiovascular death (1.0 vs 0.8/100 py, HR: 1.26, 95% CI 0.85 to 1.86) but higher stroke rate (0.7 vs 0.4/100 py, HR: 1.74, 95% CI 1.05 to 2.87) including a significant increase in ischaemic stroke during the first 6 months after switching to non-study aspirin.ConclusionDiscontinuing study rivaroxaban and aspirin to non-study aspirin was associated with the loss of cardiovascular benefits and a stroke excess.Trial registration numberNCT01776424.

scholarly journals Quit When You Can: Efficient Evaluation of Ensembles by Optimized Ordering

2021 ◽  
Vol 17 (4) ◽  
pp. 1-20
Author(s):  
Serena Wang ◽  
Maya Gupta ◽  
Seungil You
Keyword(s):  
Optimization Problem ◽  
Optimal Solution ◽  
Combinatorial Optimization Problem ◽  
Joint Optimization ◽  
Early Stopping ◽  
Time Approximation ◽  
Approximation Bound ◽  
Evaluation Time ◽  
Speed Up ◽  
Real World Problems

Given a classifier ensemble and a dataset, many examples may be confidently and accurately classified after only a subset of the base models in the ensemble is evaluated. Dynamically deciding to classify early can reduce both mean latency and CPU without harming the accuracy of the original ensemble. To achieve such gains, we propose jointly optimizing the evaluation order of the base models and early-stopping thresholds. Our proposed objective is a combinatorial optimization problem, but we provide a greedy algorithm that achieves a 4-approximation of the optimal solution under certain assumptions, which is also the best achievable polynomial-time approximation bound. Experiments on benchmark and real-world problems show that the proposed Quit When You Can (QWYC) algorithm can speed up average evaluation time by 1.8–2.7 times on even jointly trained ensembles, which are more difficult to speed up than independently or sequentially trained ensembles. QWYC’s joint optimization of ordering and thresholds also performed better in experiments than previous fixed orderings, including gradient boosted trees’ ordering.

scholarly journals Age, Sex and Cerebral Microbleed Effects On White Matter Degradation After Traumatic Brain Injury

2020 ◽  
Vol 4 (Supplement_1) ◽  
pp. 886-887
Author(s):  
Andrei Irimia ◽  
Ammar Dharani ◽  
Van Ngo ◽  
David Robles ◽  
Kenneth Rostowsky
Keyword(s):  
Traumatic Brain Injury ◽  
Brain Injury ◽  
White Matter ◽  
Diffusion Tensor ◽  
Diffuse Axonal Injury ◽  
Principal Component ◽  
Older Age ◽  
Analysis Of Covariance ◽  
Future Research ◽  
Cerebral Microbleed

Abstract Mild traumatic brain injury (mTBI) affects white matter (WM) integrity and accelerates neurodegeneration. This study assesses the effects of age, sex, and cerebral microbleed (CMB) load as predictors of WM integrity in 70 subjects aged 18-77 imaged acutely and ~6 months after mTBI using diffusion tensor imaging (DTI). Two-tensor unscented Kalman tractography was used to segment and cluster 73 WM structures and to map changes in their mean fractional anisotropy (FA), a surrogate measure of WM integrity. Dimensionality reduction of mean FA feature vectors was implemented using principal component (PC) analysis, and two prominent PCs were used as responses in a multivariate analysis of covariance. Acutely and chronically, older age was significantly associated with lower FA (F2,65 = 8.7, p < .001, η2 = 0.2; F2,65 = 12.3, p < .001, η2 = 0.3, respectively), notably in the corpus callosum and in dorsolateral temporal structures, confirming older adults’ WM vulnerability to mTBI. Chronically, sex was associated with mean FA (F2,65 = 5.0, p = 0.01, η2 = 0.1), indicating males’ greater susceptibility to WM degradation. Acutely, a significant association was observed between CMB load and mean FA (F2,65 = 5.1, p = 0.009, η2 = 0.1), suggesting that CMBs reflect the acute severity of diffuse axonal injury. Together, these findings indicate that older age, male sex, and CMB load are risk factors for WM degeneration. Future research should examine how sex- and age-mediated WM degradation lead to cognitive decline and connectome degeneration after mTBI.

Sign in / Sign up

Export Citation Format

Share Document