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 …
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 …
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 …
Efficient active learning for Gaussian process classification by error reduction
Active learning sequentially selects the best instance for labeling by optimizing an
acquisition function to enhance data/label efficiency. The selection can be either from a …
acquisition function to enhance data/label efficiency. The selection can be either from a …
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 …
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 …
Multi-objective latent space optimization of generative molecular design models
Molecular design based on generative models, such as variational autoencoders (VAEs),
has become increasingly popular in recent years due to its efficiency for exploring high …
has become increasingly popular in recent years due to its efficiency for exploring high …
A rigorous uncertainty-aware quantification framework is essential for reproducible and replicable machine learning workflows
The capability to replicate the predictions by machine learning (ML) or artificial intelligence
(AI) models and the results in scientific workflows that incorporate such ML/AI predictions is …
(AI) models and the results in scientific workflows that incorporate such ML/AI predictions is …
Deep unsupervised active learning via matrix sketching
Most existing unsupervised active learning methods aim at minimizing the data
reconstruction loss by using the linear models to choose representative samples for …
reconstruction loss by using the linear models to choose representative samples for …
Quantifying the multi-objective cost of uncertainty
Various real-world applications involve modeling complex systems with immense
uncertainty and optimizing multiple objectives based on the uncertain model. Quantifying the …
uncertainty and optimizing multiple objectives based on the uncertain model. Quantifying the …