Results 51 to 60 of about 41,144 (258)

Practical Deep Learning with Bayesian Principles

CoRR, 2019
Bayesian methods promise to fix many shortcomings of deep learning, but they are impractical and rarely match the performance of standard methods, let alone improve them. In this paper, we demonstrate practical training of deep networks with natural-gradient variational inference.
Kazuki Osawa, Siddharth Swaroop, Anirudh Jain, Runa Eschenhagen, Richard E. Turner, Rio Yokota, Mohammad Emtiyaz Khan   +6 more
openaire   +3 more sources

A Workflow to Accelerate Microstructure‐Sensitive Fatigue Life Predictions

Advanced Engineering Materials, EarlyView.
This study introduces a workflow to accelerate predictions of microstructure‐sensitive fatigue life. Results from frameworks with varying levels of simplification are benchmarked against published reference results. The analysis reveals a trade‐off between accuracy and model complexity, offering researchers a practical guide for selecting the optimal ...
Luca Loiodice, Krzysztof S. Stopka, Michael D. Sangid   +2 more
wiley   +1 more source

Machine Learning‐Supported Analysis for Predicting and Visualizing Nonlinear Relationships Between Material Properties in Electroplated Chromium Layers

Advanced Engineering Materials, EarlyView.
This study applies machine learning regression to predict chromium layer thickness in decorative trivalent chromium electroplating, using 441 experiments from laboratory‐scale (1L) and pilot‐scale (14L) setups. Tree‐based models, particularly CatBoost, outperformed linear regression by capturing nonlinear parameter interactions (R2$R^2$ up to 0.77 ...
Christoph Baumer, Christopher Mai, Luca Eisentraut, Andreas Bund, Ricardo Buettner   +4 more
wiley   +1 more source

FastNano Liquid: An Automated Platform for Small‐Angle X‐ray Scattering‐Based Materials Discovery

Advanced Engineering Materials, EarlyView.
We present FastNano Liquid, an automated small‐ and wide‐angle X‐ray scattering platform for the combined synthesis and characterization of (nano)materials. The platform is coupled to varied reactor workflows for both in situ studies of reaction kinetics and ex situ screening of synthesis conditions to support machine learning‐guided exploration ...
Pierre‐Baptiste Flandrin, Émeline Cournède, Jens Krarup, Michael Lesa, Foyzul Hasan, Amandine Séné, Arnaud Lahouati, David Benhaiem, Jérémie‐Luc Sanchez, Simon Delacroix, Thierry Gacoin, Fabienne Testard, Damien Faivre, David Carriere, Corinne Chevallard, Olivier Taché, Mark A. Levenstein   +16 more
wiley   +1 more source

Bayesian Sparsification for Deep Neural Networks With Bayesian Model Reduction

IEEE Access
Deep learning’s immense capabilities are often constrained by the complexity of its models, leading to an increasing demand for effective sparsification techniques.
Dimitrije Markovic, Karl J. Friston, Stefan J. Kiebel   +2 more
doaj   +1 more source

A COMPARATIVE ANALYSIS OF WEB INFORMATION EXTRACTION TECHNIQUES DEEP LEARNING vs. NAÏVE BAYES vs. BACK PROPAGATION NEURAL NETWORKS IN WEB DOCUMENT EXTRACTION [PDF]

ICTACT Journal on Soft Computing, 2016
Web mining related exploration is getting the chance to be more essential these days in view of the reason that a lot of information is overseen through the web. Web utilization is expanding in an uncontrolled way.
J. Sharmila, A. Subramani
doaj  

Autonomous Multi‐Objective Nanoscale Characterization of Combinatorial (Al, Sc, B)N Films Reveals Composition‐Dependent Ferroelectric Regimes

Advanced Functional Materials, EarlyView.
Autonomous scanning probe microscopy and multi‐objective Bayesian optimization navigate a ternary (Al,Sc,B)N combinatorial library. Registered photoluminescence, electron‐probe compositional mapping, and X‐ray diffraction connect local electromechanical function to defect‐sensitive emission, composition, and crystal structure.
Yu Liu, Aditya Raghavan, Utkarsh Pratiush, Ian Mercer, Pochun Hsieh, Albert Suceava, Chih‐Yu Lee, Edgar Dimitrov, Mauricio Terrones, Ichiro Takeuchi, Venkatraman Gopalan, Jon‐Paul Maria, Sergei V. Kalinin   +12 more
wiley   +1 more source

Beyond Presumptions: Toward Mechanistic Clarity in Metal‐Free Carbon Catalysts for Electrochemical H2O2 Production via Data Science

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, Hsi‐wen Wu, Xiao Wang, Jie Zhang   +3 more
wiley   +1 more source

Bayesian Computation in Deep Learning

Bayesian methods have shown success in deep learning applications. For example, in predictive tasks, Bayesian neural networks leverage Bayesian reasoning of model uncertainty to improve the reliability and uncertainty awareness of deep neural networks. In generative modeling domain, many widely used deep generative models, such as deep latent variable ...
Wenlong Chen, Bolian Li, Ruqi Zhang, Yingzhen Li   +3 more
openaire   +3 more sources

ZhuSuan: A Library for Bayesian Deep Learning

CoRR, 2017
In this paper we introduce ZhuSuan, a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep learning. ZhuSuan is built upon Tensorflow. Unlike existing deep learning libraries, which are mainly designed for deterministic neural networks and supervised tasks, ZhuSuan
Jiaxin Shi, Jianfei Chen 0001, Jun Zhu 0001, Shengyang Sun, Yucen Luo, Yihong Gu, Yuhao Zhou   +6 more
openaire   +3 more sources