Results 61 to 70 of about 199,039 (272)
BRUNO: A Deep Recurrent Model for Exchangeable Data [PDF]
, 2018 We present a novel model architecture which leverages deep learning tools to perform exact Bayesian inference on sets of high dimensional, complex observations.
Dambre, Joni +5 more
core +2 more sources
Artificial Intelligence as the Next Visionary in Liquid Crystal Research
Advanced Functional Materials, EarlyView.The functions of AI in the research laboratory are becoming increasingly sophisticated, allowing the entire process of hypothesis formulation, material design, synthesis, experimental design, and reiterative testing to be automated. In our work, we conceive how the incorporation of AI in the laboratory environment will transform the role and ...
Mert O. Astam +2 more
wiley +1 more source
Bayesian Sparsification for Deep Neural Networks With Bayesian Model Reduction
IEEE AccessDeep learning’s immense capabilities are often constrained by the complexity of its models, leading to an increasing demand for effective sparsification techniques.
Dimitrije Markovic +2 more
doaj +1 more source
Advanced Healthcare Materials, EarlyView.We developed a micro‐sized, biocompatible implant for postoperative sustained delivery of anti‐fibrotic antibodies in glaucoma surgery. Machine learning‐guided optimization of polymer composition, implant geometry, and porosity enabled precise control of drug release.
Mengqi Qin +5 more
wiley +1 more source
Isolation Defines Identity: Functional Consequences of Extracellular Vesicle Purification Strategies
Advanced Healthcare Materials, EarlyView.Four extracellular vesicle purification strategies are compared using ovarian‐cancer ascites and ES‐2 cell supernatants. A novel workflow links purification to function by combining particle‐normalized proteomics with matched cell‐free and cell‐based assays.
Christian Preußer +10 more
wiley +1 more source
Advanced Materials, EarlyView.Metal‐free carbon catalysts enable the sustainable synthesis of hydrogen peroxide via two‐electron oxygen reduction; however, active site complexity continues to hinder reliable interpretation. This review critiques correlation‐based approaches and highlights the importance of orthogonal experimental designs, standardized catalyst passports ...
Dayu Zhu +3 more
wiley +1 more source
A Hybrid Deep Learning Model for Link Dynamic Vehicle Count Forecasting with Bayesian Optimization
Journal of Advanced Transportation, 2023 The link dynamic vehicle count is a spatial variable that measures the traffic state of road sections, which reflects the actual traffic demand. This paper presents a hybrid deep learning method that combines the gated recurrent unit (GRU) neural network
Chunguang He +3 more
doaj +1 more source
Deep Bayesian Active Learning with Image Data
, 2017 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 active learning setting. First, active learning (AL) methods generally rely on being able to learn and update models from small amounts of data.
Ghahramani, Z, Gal, Y, Islam, R
openaire +3 more sources
Bayesian Deep Learning via Subnetwork Inference
Proceedings of Machine Learning Research, 2020 The Bayesian paradigm has the potential to solve core issues of deep neural networks such as poor calibration and data inefficiency. Alas, scaling Bayesian inference to large weight spaces often requires restrictive approximations. In this work, we show that it suffices to perform inference over a small subset of model weights in order to obtain ...
Daxberger, E. +4 more
openaire +4 more sources
Active Learning‐Guided Accelerated Discovery of Ultra‐Efficient High‐Entropy Thermoelectrics
Advanced Materials, EarlyView.An active learning framework is introduced for the accelerated discovery of high‐entropy chalcogenides with superior thermoelectric performance. Only 80 targeted syntheses, selected from 16206 possible combinations, led to three high‐performance compositions, demonstrating the remarkable efficiency of data‐driven guidance in experimental materials ...
Hanhwi Jang +8 more
wiley +1 more source