[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 …
A survey of active learning in collaborative filtering recommender systems
In collaborative filtering recommender systems user's preferences are expressed as ratings
for items, and each additional rating extends the knowledge of the system and affects the …
for items, and each additional rating extends the knowledge of the system and affects the …
Batchbald: Efficient and diverse batch acquisition for deep bayesian active learning
A Kirsch, J Van Amersfoort… - Advances in neural …, 2019 - proceedings.neurips.cc
We develop BatchBALD, a tractable approximation to the mutual information between a
batch of points and model parameters, which we use as an acquisition function to select …
batch of points and model parameters, which we use as an acquisition function to select …
The power of ensembles for active learning in image classification
WH Beluch, T Genewein… - Proceedings of the …, 2018 - openaccess.thecvf.com
Deep learning methods have become the de-facto standard for challenging image
processing tasks such as image classification. One major hurdle of deep learning …
processing tasks such as image classification. One major hurdle of deep learning …
Deep bayesian active learning with image data
Even though active learning forms an important pillar of machine learning, deep learning
tools are not prevalent within it. Deep learning poses several difficulties when used in an …
tools are not prevalent within it. Deep learning poses several difficulties when used in an …
Active domain randomization
Abstract Domain randomization is a popular technique for improving domain transfer, often
used in a zero-shot setting when the target domain is unknown or cannot easily be used for …
used in a zero-shot setting when the target domain is unknown or cannot easily be used for …
Committee-based active learning for surrogate-assisted particle swarm optimization of expensive problems
Function evaluations (FEs) of many real-world optimization problems are time or resource
consuming, posing a serious challenge to the application of evolutionary algorithms (EAs) to …
consuming, posing a serious challenge to the application of evolutionary algorithms (EAs) to …
Bayesian deep-learning-based health prognostics toward prognostics uncertainty
Deep-learning-based health prognostics is receiving ever-increasing attention. Most existing
methods leverage advanced neural networks for prognostics performance improvement …
methods leverage advanced neural networks for prognostics performance improvement …
Surrogate-assisted evolutionary computation: Recent advances and future challenges
Y Jin - Swarm and Evolutionary Computation, 2011 - Elsevier
Surrogate-assisted, or meta-model based evolutionary computation uses efficient
computational models, often known as surrogates or meta-models, for approximating the …
computational models, often known as surrogates or meta-models, for approximating the …
Active learning literature survey
B Settles - 2009 - minds.wisconsin.edu
The key idea behind active learning is that a machine learning algorithm can achieve
greater accuracy with fewer labeled training instances if it is allowed to choose the training …
greater accuracy with fewer labeled training instances if it is allowed to choose the training …