A survey on active learning: State-of-the-art, practical challenges and research directions
A Tharwat, W Schenck - Mathematics, 2023 - mdpi.com
Despite the availability and ease of collecting a large amount of free, unlabeled data, the
expensive and time-consuming labeling process is still an obstacle to labeling a sufficient …
expensive and time-consuming labeling process is still an obstacle to labeling a sufficient …
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 …
Optimizing sequential experimental design with deep reinforcement learning
Bayesian approaches developed to solve the optimal design of sequential experiments are
mathematically elegant but computationally challenging. Recently, techniques using …
mathematically elegant but computationally challenging. Recently, techniques using …
Revisiting logistic-softmax likelihood in bayesian meta-learning for few-shot classification
Meta-learning has demonstrated promising results in few-shot classification (FSC) by
learning to solve new problems using prior knowledge. Bayesian methods are effective at …
learning to solve new problems using prior knowledge. Bayesian methods are effective at …
Phase stability through machine learning
R Arróyave - Journal of Phase Equilibria and Diffusion, 2022 - Springer
Understanding the phase stability of a chemical system constitutes the foundation of
materials science. Knowledge of the equilibrium state of a system under arbitrary …
materials science. Knowledge of the equilibrium state of a system under arbitrary …
Bayesian Estimate of Mean Proper Scores for Diversity-Enhanced Active Learning
The effectiveness of active learning largely depends on the sampling efficiency of the
acquisition function. Expected Loss Reduction (ELR) focuses on a Bayesian estimate of the …
acquisition function. Expected Loss Reduction (ELR) focuses on a Bayesian estimate of the …
Hypothesis Perturbation for Active Learning
SJ Cho, G Kim, CD Yoo - IEEE Journal of Selected Topics in …, 2024 - ieeexplore.ieee.org
This paper introduces a computationally efficient Query-by-Committee (QBC) algorithm
specifically designed for deep active learning. This approach leverages the concept of …
specifically designed for deep active learning. This approach leverages the concept of …
Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions
A Kirsch - arXiv preprint arXiv:2401.04305, 2024 - arxiv.org
At its core, this thesis aims to enhance the practicality of deep learning by improving the
label and training efficiency of deep learning models. To this end, we investigate data subset …
label and training efficiency of deep learning models. To this end, we investigate data subset …
Querying Easily Flip-flopped Samples for Deep Active Learning
Active learning is a machine learning paradigm that aims to improve the performance of a
model by strategically selecting and querying unlabeled data. One effective selection …
model by strategically selecting and querying unlabeled data. One effective selection …
Knowledge-driven learning, optimization, and experimental design under uncertainty for materials discovery
Significant acceleration of the future discovery of novel functional materials requires a
fundamental shift from the current materials discovery practice, which is heavily dependent …
fundamental shift from the current materials discovery practice, which is heavily dependent …