[HTML][HTML] A review of uncertainty quantification in deep learning: Techniques, applications and challenges
Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of
uncertainties during both optimization and decision making processes. They have been …
uncertainties during both optimization and decision making processes. They have been …
Artificial intelligence for science in quantum, atomistic, and continuum systems
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural
sciences. Today, AI has started to advance natural sciences by improving, accelerating, and …
sciences. Today, AI has started to advance natural sciences by improving, accelerating, and …
Learnable Bernoulli dropout for Bayesian deep learning
In this work, we propose learnable Bernoulli dropout (LBD), a new model-agnostic dropout
scheme that considers the dropout rates as parameters jointly optimized with other model …
scheme that considers the dropout rates as parameters jointly optimized with other model …
Varigrow: Variational architecture growing for task-agnostic continual learning based on bayesian novelty
Continual Learning (CL) is the problem of sequentially learning a set of tasks and preserving
all the knowledge acquired. Many existing methods assume that the data stream is explicitly …
all the knowledge acquired. Many existing methods assume that the data stream is explicitly …
A survey of challenges and opportunities in sensing and analytics for risk factors of cardiovascular disorders
Cardiovascular disorders cause nearly one in three deaths in the United States. Short-and
long-term care for these disorders is often determined in short-term settings. However, these …
long-term care for these disorders is often determined in short-term settings. However, these …
Uncertainty quantification for deep context-aware mobile activity recognition and unknown context discovery
Activity recognition in wearable computing faces two key challenges: i) activity
characteristics may be context-dependent and change under different contexts or situations; …
characteristics may be context-dependent and change under different contexts or situations; …
VFDS: Variational Foresight Dynamic Selection in Bayesian Neural Networks for Efficient Human Activity Recognition
In many machine learning tasks, input features with varying degrees of predictive capability
are acquired at varying costs. In order to optimize the performance-cost trade-off, one would …
are acquired at varying costs. In order to optimize the performance-cost trade-off, one would …
Towards Robust and Generalizable Machine Learning for Real-World Healthcare Data with Heterogeneity
Z Huo - 2022 - search.proquest.com
The utility of machine learning for enhancing human well-being and health has risen to the
core discussion in both research and real-world application in today's technological front …
core discussion in both research and real-world application in today's technological front …
Deep Semi-Supervised and Multi-Stage Learning for Medical Applications
NC Hurley - 2022 - oaktrust.library.tamu.edu
Machine learning techniques are widely used to build models for applications in healthcare.
These models typically predict likelihood of a particular patient outcome in a given setting …
These models typically predict likelihood of a particular patient outcome in a given setting …
Dynamic Feature Selection for Efficient and Interpretable Human Activity Recognition
In many machine learning tasks, input features with varying degrees of predictive capability
are usually acquired at some cost. For example, in human activity recognition (HAR) and …
are usually acquired at some cost. For example, in human activity recognition (HAR) and …