Self-driving laboratories for chemistry and materials science

G Tom, SP Schmid, SG Baird, Y Cao, K Darvish… - Chemical …, 2024 - ACS Publications
Self-driving laboratories (SDLs) promise an accelerated application of the scientific method.
Through the automation of experimental workflows, along with autonomous experimental …

[HTML][HTML] Automated machine learning: Review of the state-of-the-art and opportunities for healthcare

J Waring, C Lindvall, R Umeton - Artificial intelligence in medicine, 2020 - Elsevier
Objective This work aims to provide a review of the existing literature in the field of
automated machine learning (AutoML) to help healthcare professionals better utilize …

SMAC3: A versatile Bayesian optimization package for hyperparameter optimization

M Lindauer, K Eggensperger, M Feurer… - Journal of Machine …, 2022 - jmlr.org
Algorithm parameters, in particular hyperparameters of machine learning algorithms, can
substantially impact their performance. To support users in determining well-performing …

Could graph neural networks learn better molecular representation for drug discovery? A comparison study of descriptor-based and graph-based models

D Jiang, Z Wu, CY Hsieh, G Chen, B Liao… - Journal of …, 2021 - Springer
Graph neural networks (GNN) has been considered as an attractive modelling method for
molecular property prediction, and numerous studies have shown that GNN could yield …

Speech emotion recognition using deep 1D & 2D CNN LSTM networks

J Zhao, X Mao, L Chen - Biomedical signal processing and control, 2019 - Elsevier
We aimed at learning deep emotion features to recognize speech emotion. Two
convolutional neural network and long short-term memory (CNN LSTM) networks, one 1D …

Auto-keras: An efficient neural architecture search system

H **, Q Song, X Hu - Proceedings of the 25th ACM SIGKDD …, 2019 - dl.acm.org
Neural architecture search (NAS) has been proposed to automatically tune deep neural
networks, but existing search algorithms, eg, NASNet, PNAS, usually suffer from expensive …

[HTML][HTML] Prediction of undrained shear strength using extreme gradient boosting and random forest based on Bayesian optimization

W Zhang, C Wu, H Zhong, Y Li, L Wang - Geoscience Frontiers, 2021 - Elsevier
Accurate assessment of undrained shear strength (USS) for soft sensitive clays is a great
concern in geotechnical engineering practice. This study applies novel data-driven extreme …

Higgs physics at the HL-LHC and HE-LHC

M Cepeda, S Gori, P Ilten, M Kado, F Riva… - arxiv preprint arxiv …, 2019 - arxiv.org
The discovery of the Higgs boson in 2012, by the ATLAS and CMS experiments, was a
success achieved with only a percent of the entire dataset foreseen for the LHC. It opened a …

Tunability: Importance of hyperparameters of machine learning algorithms

P Probst, AL Boulesteix, B Bischl - Journal of Machine Learning Research, 2019 - jmlr.org
Modern supervised machine learning algorithms involve hyperparameters that have to be
set before running them. Options for setting hyperparameters are default values from the …

Computational discovery of transition-metal complexes: from high-throughput screening to machine learning

A Nandy, C Duan, MG Taylor, F Liu, AH Steeves… - Chemical …, 2021 - ACS Publications
Transition-metal complexes are attractive targets for the design of catalysts and functional
materials. The behavior of the metal–organic bond, while very tunable for achieving target …