The rapid growth of deep learning research, including within the field of computational mechanics, has resulted in an extensive and diverse body of literat
Since the deep learning is now a hot topic in computational mechanics with neural networks and many related studies have been reported recently, we discuss here some features of computational mechanics with deep learning. First, similarity and difference between conventional neural networks and deep neu...
We present a machine learning approach that integrates geometric deep learning and Sobolev training to generate a family of finite strain anisotropic hyperelastic models that predict the homogenized responses of polycrystals previously unseen during the training. While hand-crafted hyperel...
The present paper describes a method to enhance the capability of, or to broaden the scope of computational mechanics by using deep learning, which is one of the machine learning methods and is based on the artificial neural network. The method utilizes deep learning to extract rules inherent in...
Physics-informed deep learning is a novel approach recently developed for modeling PDE solutions and shows promise to solve computational mechanics problems without using any labeled data. The philosophy behind it is to approximate the quantity of interest (e.g., PDE solution variables) by a deep ...
pdf (Laboratory of Computational Physics, Institute of Applied Physics and Computational Mathematics, Beijing; CAEP Software Center for High Performance Numerical Simulation, Beijing) Han Wang(王涵), Linfeng Zhang(张林峰), Jiequn Han(韩劼群), and Weinan E(鄂维南), DeePMD-kit: a deep learning ...
and the generated innumerable datasets resulted in complexities during analysis. The deep learning (DL) technique used in this study provides a good solution, as it can effectively learn the hidden patterns from a large number of datasets. The DL approach builds predictive models with multiple level...
learning has led to rapid growth in algorithms and methods for solving a variety of ill-posed inverse computational imaging problems45, such as super-resolution microscopy46, lensless phase imaging47, computational ghost imaging48, and image through scattering media49. In this context, researchers in...
Comparing the prediction performance of a Deep Learning Neural Network model with conventional machine learning models in landslide susceptibility assessment.Catena188, 104426 [16] Bui, D.T., Tuan, T.A., Klempe, H., Pradhan, B., Revhaug, I., 2016b. Spatial prediction models for shallow ...
The present chapter overviews recent research trends of deep learning related to computational mechanics. In Sect. 3.1 , we see the growing interest in deep learning in recent years based on the trend of the number of published papers on this topic, discussing how deep learning is applied to ...