Results 41 to 50 of about 227,027 (269)

Phase Transitions of Neural Networks

, 1997
The cooperative behaviour of interacting neurons and synapses is studied using models and methods from statistical physics. The competition between training error and entropy may lead to discontinuous properties of the neural network.
Biehl M., Opper M., Wolfgang Kinzel, Yeomans J.   +3 more
core   +1 more source

Active Learning‐Accelerated Discovery of Fibrous Hydrogels with Tissue‐Mimetic Viscoelasticity

Advanced Functional Materials, EarlyView.
Active learning accelerates the design of fibrous hydrogels that mimic the viscoelasticity of native tissues. By integrating multi‐objective optimization and closed‐loop experimentation, this approach efficiently identifies optimal formulations from thousands of possibilities and decouples elasticity and viscosity. The resulting hydrogels offer tunable
Zhengkun Chen, Zheyuan Miao, Gary Tom, Austin H. Cheng, Elizaveta Gusarova, Benjamen Zondag, Tianyi Wu, Dianoosh Kalhori, Boris Hinz, Milad Abolhasani, Alán Aspuru‐Guzik, Eugenia Kumacheva   +11 more
wiley   +1 more source

Deep Learning Neural Networks and Bayesian Neural Networks in Data Analysis

EPJ Web of Conferences, 2017
Most of the modern analyses in high energy physics use signal-versus-background classification techniques of machine learning methods and neural networks in particular.
Chernoded Andrey, Dudko Lev, Myagkov Igor, Volkov Petr   +3 more
doaj   +1 more source

Bayesian neural networks for fast SUSY predictions

Physics Letters B, 2021
One of the goals of current particle physics research is to obtain evidence for new physics, that is, physics beyond the Standard Model (BSM), at accelerators such as the Large Hadron Collider (LHC) at CERN.
B.S. Kronheim, M.P. Kuchera, H.B. Prosper, A. Karbo   +3 more
doaj   +1 more source

Machine Learning‐Assisted Inverse Design of Soft and Multifunctional Hybrid Liquid Metal Composites

Advanced Functional Materials, EarlyView.
A machine learning framework is presented for inverse design of synthesizable multifunctional composites containing both liquid metal and solid inclusions. By integrating physics‐based modeling, data‐driven prediction, and Bayesian optimization, the approach enables intelligent design of experiments to identify optimal compositions and realize these ...
Lijun Zhou, Yunsik Ohm, Ren‐Mian Chin, Olivia Kerr, Krithika Manohar, Mohammad H. Malakooti   +5 more
wiley   +1 more source

The Deep Weight Prior [PDF]

, 2019
Bayesian inference is known to provide a general framework for incorporating prior knowledge or specific properties into machine learning models via carefully choosing a prior distribution.
Ashukha, Arsenii, Atanov, Andrei, Struminsky, Kirill, Vetrov, Dmitry, Welling, Max   +4 more
core   +1 more source

Bayesian Neural Networks

Journal of the Brazilian Computer Society, 1997
Bayesian techniques have been developed over many years in a range of different fields, but have only recently been applied to the problem of learning in neural networks. As well as providing a consistent framework for statistical pattern recognition, the Bayesian approach offers a number of practical advantages including a solution to the problem of ...
openaire   +3 more sources

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

Generalisation for neural networks through data sampling and training procedures, with applications to streamflow predictions [PDF]

Hydrology and Earth System Sciences, 2004
Since the 1990s, neural networks have been applied to many studies in hydrology and water resources. Extensive reviews on neural network modelling have identified the major issues affecting modelling performance; one of the most important is ...
F. Anctil, F. Anctil, N. Lauzon, N. Lauzon   +3 more
doaj  

Self‐Assembled Monolayers in p–i–n Perovskite Solar Cells: Molecular Design, Interfacial Engineering, and Machine Learning–Accelerated Material Discovery

Advanced Materials, EarlyView.
This review highlights the role of self‐assembled monolayers (SAMs) in perovskite solar cells, covering molecular engineering, multifunctional interface regulation, machine learning (ML) accelerated discovery, advanced device architectures, and pathways toward scalable fabrication and commercialization for high‐efficiency and stable single‐junction and
Asmat Ullah, Ying Luo, Stefaan De Wolf
wiley   +1 more source