Efficient sampling-based Bayesian Active Learning for synaptic characterization. [PDF]
PLoS Computational Biology, 2023 Bayesian Active Learning (BAL) is an efficient framework for learning the parameters of a model, in which input stimuli are selected to maximize the mutual information between the observations and the unknown parameters. However, the applicability of BAL
Camille Gontier +4 more
doaj +4 more sources
Turn-key constrained parameter space exploration for particle accelerators using Bayesian active learning [PDF]
Nature Communications, 2021 Characterizing an unknown, complex system, like an accelerator, in multi-dimensional space is a challenging task. Here the authors report a Bayesian active learning method - Constrained Proximal Bayesian Exploration - for the characterization of a ...
Ryan Roussel +8 more
doaj +2 more sources
On-the-fly closed-loop materials discovery via Bayesian active learning [PDF]
Nature Communications, 2020 Machine learning driven research holds big promise towards accelerating materials’ discovery. Here the authors demonstrate CAMEO, which integrates active learning Bayesian optimization with practical experiments execution, for the discovery of new phase-
A. Gilad Kusne +15 more
doaj +2 more sources
Fast Posterior Estimation of Cardiac Electrophysiological Model Parameters via Bayesian Active Learning [PDF]
Frontiers in Physiology, 2021 Probabilistic estimation of cardiac electrophysiological model parameters serves an important step toward model personalization and uncertain quantification.
Md Shakil Zaman +7 more
doaj +2 more sources
Efficient structure learning of gene regulatory networks with Bayesian active learning [PDF]
BMC BioinformaticsBackground Gene regulatory network modeling is a complex structure learning problem that involves both observational data analysis and experimental interventions.
Dániel Sándor, Péter Antal
doaj +2 more sources
Multi-objective Bayesian active learning for MeV-ultrafast electron diffraction [PDF]
Nature CommunicationsUltrafast electron diffraction using MeV energy beams(MeV-UED) has enabled unprecedented scientific opportunities in the study of ultrafast structural dynamics in a variety of gas, liquid and solid state systems.
Fuhao Ji +15 more
doaj +2 more sources
Bayesian active learning with model selection for spectral experiments [PDF]
Scientific ReportsActive learning is a common approach to improve the efficiency of spectral experiments. Model selection from the candidates and parameter estimation are often required in the analysis of spectral experiments.
Tomohiro Nabika +4 more
doaj +2 more sources
Active Learning with Bayesian UNet for Efficient Semantic Image Segmentation
Journal of Imaging, 2021 We present a sample-efficient image segmentation method using active learning, we call it Active Bayesian UNet, or AB-UNet. This is a convolutional neural network using batch normalization and max-pool dropout.
Isah Charles Saidu, Lehel Csató
doaj +3 more sources
Knowledge graph-aided Bayesian active learning for top-K genetic interaction discovery [PDF]
Scientific ReportsIn silico methods for predicting the effects of multi-gene perturbations hold great promise for advancing functional genomics, computational drug discovery, and disease modeling.
Braden Soper +7 more
doaj +2 more sources
A Bayesian active learning platform for scalable combination drug screens [PDF]
Nature CommunicationsLarge-scale combination drug screens are generally considered intractable due to the immense number of possible combinations. Existing approaches use ad hoc fixed experimental designs then train machine learning models to impute unobserved combinations ...
Christopher Tosh +8 more
doaj +2 more sources