NEXTorch: A Design and Bayesian Optimization Toolkit for Chemical Sciences and Engineering

NEXTorch: A Design and Bayesian Optimization Toolkit for Chemical Sciences and Engineering

Automation and optimization of chemical systems require well-inform decisions on what experiments to run to reduce time, materials, and/or computations. Data-driven active learning algorithms have emerged as valuable tools to solve such tasks. Bayesian optimization, a sequential global optimization approach, is a popular active-learning framework. Past studies have demonstrated its efficiency in solving chemistry and engineering problems. We introduce NEXTorch, a library in Python/PyTorch, to facilitate laboratory or computational design using Bayesian optimization. NEXTorch offers fast predictive modeling, flexible optimization loops, visualization capabilities, easy interfacing with legacy software, and multiple types of parameters and data type conversions. It provides GPU acceleration, parallelization, and state-of-the-art Bayesian Optimization algorithms and supports both automated and human-in-the-loop optimization. The comprehensive online documentation introduces Bayesian optim

1 mentions: @KwhRd100
Date: 2021/06/10 15:19

Referring Tweets

@KwhRd100 NEXTorch: 化学科学および工学のための設計およびベイズ最適化ツールキット 様々な種類のパラメータやデータタイプの変換に対応し、自動および人間によるループ内の最適化をサポートし、様々な視覚化を実現するNEXTorchの提案。GPU/並列化対応済のPython/PyTorch実装あり。

Related Entries

Read more Materials | Free Full-Text | A Deep Neural Network for Accurate and Robust Prediction of the Glass ...
0 users, 1 mentions 2020/12/26 15:51
Read more [2012.13002] Robust approximation of tensor networks: application to grid-free tensor factorization ...
0 users, 1 mentions 2021/01/04 15:51
Read more [2102.10240] Learning Neural Generative Dynamics for Molecular Conformation Generation
0 users, 1 mentions 2021/02/24 15:52
Read more [2103.03633] Unveiling the Glass Veil: Elucidating the Optical Properties in Glasses with Interpreta...
0 users, 1 mentions 2021/03/08 15:52
Read more [2104.11159] An End-to-End Computer Vision Methodology for Quantitative Metallography
0 users, 1 mentions 2021/04/24 16:48
Read more [2104.14661] Random Embeddings and Linear Regression can Predict Protein Function
0 users, 1 mentions 2021/05/03 16:48



安定したサイト運営のためにGitHub sponsorを募集しています。