Results 61 to 70 of about 7,921,142 (232)

Physics-informed machine learning

Nature Reviews Physics, 2021
G. Karniadakis, I. Kevrekidis, Lu Lu, P. Perdikaris, Sifan Wang, Liu Yang   +5 more
semanticscholar   +1 more source

Accelerating crystal structure search through active learning with neural networks for rapid relaxations

npj Computational Materials
Global optimization of crystal compositions is a significant yet computationally intensive method to identify stable structures within chemical space.
Stefaan S. P. Hessmann, Kristof T. Schütt, Niklas W. A. Gebauer, Michael Gastegger, Tamio Oguchi, Tomoki Yamashita   +5 more
doaj   +1 more source

A Machine Learning-Oriented Survey on Tiny Machine Learning

IEEE Access
The emergence of Tiny Machine Learning (TinyML) has positively revolutionized the field of Artificial Intelligence by promoting the joint design of resource-constrained IoT hardware devices and their learning-based software architectures. TinyML carries an essential role within the fourth and fifth industrial revolutions in helping societies, economies,
Capogrosso, Luigi, Cunico, Federico, Cheng, Dong Seon, Fummi, Franco, Cristani, Marco   +4 more
openaire   +4 more sources

3D scattering transforms for disease classification in neuroimaging

NeuroImage: Clinical, 2017
Classifying neurodegenerative brain diseases in MRI aims at correctly assigning discrete labels to MRI scans. Such labels usually refer to a diagnostic decision a learner infers based on what it has learned from a training sample of MRI scans ...
Tameem Adel, Taco Cohen, Matthan Caan, Max Welling   +3 more
doaj   +1 more source

Learning as a Machine. Crossovers Between Humans and Machines

Journal of Learning Analytics, 2017
This article introduces the special issue from SoLAR’s 2016 Learning Analytics and Knowledge conference. The field of learning analytics (LA) draws heavily on theory and practice from a range of diverse academic disciplines. In so doing, LA research embodies a rich integration of methodologies and practices, assumptions and theory to bring new insights
openaire   +4 more sources

A Probabilistic Adversarial Autoencoder for Novelty Detection: Leveraging Lightweight Design and Reconstruction Loss

IEEE Access
A novelty detection task involves identifying whether a data point is an outlier, given a training dataset that primarily captures the distribution of inliers. The novel class is usually absent, poorly sampled, or not well defined in the training data. A
Muhammad Asad, Ihsan Ullah, Muhammad Adeel Hafeez, Ganesh Sistu, Michael G. Madden   +4 more
doaj   +1 more source

Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions

Nature Communications, 2019
Machine learning models can accurately predict atomistic chemical properties but do not provide access to the molecular electronic structure. Here the authors use a deep learning approach to predict the quantum mechanical wavefunction at high efficiency ...
K. T. Schütt, M. Gastegger, A. Tkatchenko, K.-R. Müller, R. J. Maurer   +4 more
doaj   +1 more source

Deep Learning‐Based Postprocessing to Enhance Subseasonal Soil Moisture Forecasts Over Europe

Journal of Geophysical Research: Machine Learning and Computation
Accurate forecasts on subseasonal (S2S) timescales are essential for the preparation and mitigation of the impacts of high‐impact events, such as flash droughts.
Noelia Otero, Atahan Özer, Jackie Ma
doaj   +1 more source

Deterministic Uncertainty Estimation for Multi-Modal Regression With Deep Neural Networks

IEEE Access
Prediction interval (PI) is a common method to represent predictive uncertainty in regression by deep neural networks. This paper proposes an extension of the prediction interval by using a union of disjoint intervals. Since previous PI methods assumed a
Jaehak Cho, Jae Myung Kim, Seungyub Han, Jungwoo Lee   +3 more
doaj   +1 more source

Climate data selection for multi-decadal wind power forecasts

Environmental Research Letters
Reliable wind speed data is crucial for applications such as estimating local (future) wind power. Global climate models (GCMs) and regional climate models (RCMs) provide forecasts over multi-decadal periods.
Sofia Morelli, Nina Effenberger, Luca Schmidt, Nicole Ludwig   +3 more
doaj   +1 more source