In recent years, deep neural networks (DNNs) based approaches have achieved the start-of-the-art performance for music source separation (MSS).
Speech enhancement methods based on deep learning have surpassed traditional methods.
In this work, a new causal U-net based multiple-in-multiple-out structure is proposed for real-time multi-channel speech enhancement.
We investigate the solution landscapes of the confined diblock copolymer and homopolymer in two-dimensional domain by using the extended Ohta--Kawasaki model.
Soft Condensed Matter Computational Physics
In this paper, we propose a style-guided data augmentation for repairing DNN in the operational environment.
The scarcity of class-labeled data is a ubiquitous bottleneck in many machine learning problems.
Besides, the attack is further enhanced by adaptively tuning the translations of object and background.
Regularization plays a crucial role in machine learning models, especially for deep neural networks.
4 code implementations • 6 Nov 2019 • Vijay Janapa Reddi, Christine Cheng, David Kanter, Peter Mattson, Guenther Schmuelling, Carole-Jean Wu, Brian Anderson, Maximilien Breughe, Mark Charlebois, William Chou, Ramesh Chukka, Cody Coleman, Sam Davis, Pan Deng, Greg Diamos, Jared Duke, Dave Fick, J. Scott Gardner, Itay Hubara, Sachin Idgunji, Thomas B. Jablin, Jeff Jiao, Tom St. John, Pankaj Kanwar, David Lee, Jeffery Liao, Anton Lokhmotov, Francisco Massa, Peng Meng, Paulius Micikevicius, Colin Osborne, Gennady Pekhimenko, Arun Tejusve Raghunath Rajan, Dilip Sequeira, Ashish Sirasao, Fei Sun, Hanlin Tang, Michael Thomson, Frank Wei, Ephrem Wu, Lingjie Xu, Koichi Yamada, Bing Yu, George Yuan, Aaron Zhong, Peizhao Zhang, Yuchen Zhou
Machine-learning (ML) hardware and software system demand is burgeoning.
Convolutional neural networks (CNNs) have achieved remarkable performance in various fields, particularly in the domain of computer vision.
Along this line, we theoretically study a general form of gradient based optimization dynamics with unbiased noise, which unifies SGD and standard Langevin dynamics.
In this U-shaped network, a paired sampling operation is proposed in spacetime domain accordingly: the pooling (ST-Pool) coarsens the input graph in spatial from its deterministic partition while abstracts multi-resolution temporal dependencies through dilated recurrent skip connections; based on previous settings in the downsampling, the unpooling (ST-Unpool) restores the original structure of spatio-temporal graphs and resumes regular intervals within graph sequences.
Ranked #1 on Traffic Prediction on PeMS-M
(2) We propose an original 3D graph convolution model to model the spatio-temporal data more accurately.
Ranked #2 on Traffic Prediction on PeMS-M
The proposed TNAR is composed by two complementary parts, the tangent adversarial regularization (TAR) and the normal adversarial regularization (NAR).
Along this line, we study a general form of gradient based optimization dynamics with unbiased noise, which unifies SGD and standard Langevin dynamics.
We propose a deep learning based method, the Deep Ritz Method, for numerically solving variational problems, particularly the ones that arise from partial differential equations.
Timely accurate traffic forecast is crucial for urban traffic control and guidance.
Ranked #2 on Time Series Forecasting on PeMSD7