Deep Kronecker neural networks: A general framework for neural networks with adaptive activation functions
TLDR
In this paper, the authors proposed a new type of neural networks, Kronecker neural networks (KNNs), which form a general framework for neural networks with adaptive activation functions.About:
This article is published in Neurocomputing.The article was published on 2022-01-11 and is currently open access. It has received 36 citations till now. The article focuses on the topics: Activation function & Artificial neural network.read more
Citations
More filters
Journal ArticleDOI
Deep learning of inverse water waves problems using multi-fidelity data: Application to Serre-Green-Naghdi equations
TL;DR: In this article , a physics-informed neural network (PINN) is used to solve the inverse water wave problem. But the authors consider strongly nonlinear and weakly dispersive surface water waves governed by equations of Boussinesq type, known as the Serre-Green-Naghdi system.
Journal ArticleDOI
Physics-informed attention-based neural network for hyperbolic partial differential equations: application to the Buckley–Leverett problem
Ruben Rodriguez-Torrado,Pablo C. Tintinago Ruiz,Luis Cueto-Felgueroso,Michael Cerny Green,Tyler Friesen,Sebastien Francois Matringe,Julian Togelius +6 more
TL;DR: In this paper , a physics-informed attention-based neural network (PIANN) is proposed to learn the complex behavior of non-linear PDEs with dominant hyperbolic character.
Journal ArticleDOI
Mitigating tunnel-induced damages using deep neural networks
Yue Pan,Limao Zhang +1 more
TL;DR: In this article , the authors proposed a data-driven decision support framework based on the integration of deep neural network and gradient descent technique (DNN-GDO) for intelligent risk prediction and optimization in the shield tunnel excavation under uncertainty.
Journal ArticleDOI
Breast Cancer Mammograms Classification Using Deep Neural Network and Entropy-Controlled Whale Optimization Algorithm
TL;DR: In this article , the Modified Entropy Whale Optimization Algorithm (MEWOA) is proposed based on fusion for deep feature extraction and perform the classification, which achieved the maximum accuracy achieved in INbreast dataset is 99.7%, MIAS dataset has 99.8% and CBIS-DDSM has 93.8%.
Journal ArticleDOI
Reliable extrapolation of deep neural operators informed by physics or sparse observations
TL;DR: In this paper , the authors investigate the extrapolation behavior of DeepONets by quantifying the 2-Wasserstein distance between two function spaces and propose a new strategy of bias-variance trade-off for extrapolation with respect to model capacity.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Journal Article
Scikit-learn: Machine Learning in Python
Fabian Pedregosa,Gaël Varoquaux,Alexandre Gramfort,Vincent Michel,Bertrand Thirion,Olivier Grisel,Mathieu Blondel,Peter Prettenhofer,Ron Weiss,Vincent Dubourg,Jake Vanderplas,Alexandre Passos,David Cournapeau,Matthieu Brucher,Matthieu Perrot,Edouard Duchesnay +15 more
TL;DR: Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems, focusing on bringing machine learning to non-specialists using a general-purpose high-level language.
Journal ArticleDOI
Deep learning
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.