Hybrid inverse design of photonic structures by combining optimization methods with neural networks

L Deng, Y Xu, Y Liu - Photonics and Nanostructures-Fundamentals and …, 2022 - Elsevier
Over the past decades, classical optimization methods, including gradient-based topology
optimization and the evolutionary algorithm, have been widely employed for the inverse …

Simulation intelligence: Towards a new generation of scientific methods

A Lavin, D Krakauer, H Zenil, J Gottschlich… - arXiv preprint arXiv …, 2021 - arxiv.org
The original" Seven Motifs" set forth a roadmap of essential methods for the field of scientific
computing, where a motif is an algorithmic method that captures a pattern of computation …

Recent advances on machine learning for computational fluid dynamics: A survey

H Wang, Y Cao, Z Huang, Y Liu, P Hu, X Luo… - arXiv preprint arXiv …, 2024 - arxiv.org
This paper explores the recent advancements in enhancing Computational Fluid Dynamics
(CFD) tasks through Machine Learning (ML) techniques. We begin by introducing …

Inverse deep learning methods and benchmarks for artificial electromagnetic material design

S Ren, A Mahendra, O Khatib, Y Deng, WJ Padilla… - Nanoscale, 2022 - pubs.rsc.org
In this work we investigate the use of deep inverse models (DIMs) for designing artificial
electromagnetic materials (AEMs)–such as metamaterials, photonic crystals, and …

Benchmarking deep inverse models over time, and the neural-adjoint method

S Ren, W Padilla, J Malof - Advances in Neural Information …, 2020 - proceedings.neurips.cc
We consider the task of solving generic inverse problems, where one wishes to determine
the hidden parameters of a natural system that will give rise to a particular set of …

Amortized inference with user simulations

HS Moon, A Oulasvirta, B Lee - Proceedings of the 2023 CHI Conference …, 2023 - dl.acm.org
There have been significant advances in simulation models predicting human behavior
across various interactive tasks. One issue remains, however: identifying the parameter …

Stabilizing invertible neural networks using mixture models

P Hagemann, S Neumayer - Inverse Problems, 2021 - iopscience.iop.org
In this paper, we analyze the properties of invertible neural networks, which provide a way of
solving inverse problems. Our main focus lies on investigating and controlling the Lipschitz …

Inverse design of two-dimensional materials with invertible neural networks

V Fung, J Zhang, G Hu, P Ganesh… - npj Computational …, 2021 - nature.com
The ability to readily design novel materials with chosen functional properties on-demand
represents a next frontier in materials discovery. However, thoroughly and efficiently …

A hybrid deep learning approach for the design of 2D low porosity auxetic metamaterials

C Zhang, J Xie, A Shanian, M Kibsey… - Engineering Applications of …, 2023 - Elsevier
Due to the remarkable ability of Deep learning (DL) to abstract hidden information, it has
been proven to be a powerful tool in many tasks related to the design of metamaterials. DL …

Invertible modeling of bidirectional relationships in neuroimaging with normalizing flows: application to brain aging

M Wilms, JJ Bannister, P Mouches… - … on Medical Imaging, 2022 - ieeexplore.ieee.org
Many machine learning tasks in neuroimaging aim at modeling complex relationships
between a brain's morphology as seen in structural MR images and clinical scores and …