English
Related papers

Related papers: SparkNet: Training Deep Networks in Spark

200 papers

Spiking neural networks (SNNs) have shown clear advantages over traditional artificial neural networks (ANNs) for low latency and high computational efficiency, due to their event-driven nature and sparse communication. However, the…

Neural and Evolutionary Computing · Computer Science 2020-07-03 Jibin Wu , Chenglin Xu , Daquan Zhou , Haizhou Li , Kay Chen Tan

Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Mathematically, ResNet architectures can be…

Optimization and Control · Mathematics 2019-07-26 S. Günther , L. Ruthotto , J. B. Schroder , E. C. Cyr , N. R. Gauger

We present QuickNet, a fast and accurate network architecture that is both faster and significantly more accurate than other fast deep architectures like SqueezeNet. Furthermore, it uses less parameters than previous networks, making it…

Machine Learning · Computer Science 2017-01-13 Tapabrata Ghosh

Deep unfolding networks have recently gained popularity in the context of solving imaging inverse problems. However, the computational and memory complexity of data-consistency layers within traditional deep unfolding networks scales with…

Image and Video Processing · Electrical Eng. & Systems 2021-06-04 Jiaming Liu , Yu Sun , Weijie Gan , Xiaojian Xu , Brendt Wohlberg , Ulugbek S. Kamilov

Convolutional Neural Networks (CNN) increase depth by stacking convolutional layers, and deeper network models perform better in image recognition. Empirical research shows that simply stacking convolutional layers does not make the network…

Computer Vision and Pattern Recognition · Computer Science 2022-11-16 Rui-Yang Ju , Jen-Shiun Chiang , Chih-Chia Chen , Yu-Shian Lin

GPUs are currently the platform of choice for training neural networks. However, training a deep neural network (DNN) is a time-consuming process even on GPUs because of the massive number of parameters that have to be learned. As a result,…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-05-29 Behnam Pourghassemi , Chenghao Zhang , Joo Hwan Lee , Aparna Chandramowlishwaran

Despite the remarkable progress recently made in distant speech recognition, state-of-the-art technology still suffers from a lack of robustness, especially when adverse acoustic conditions characterized by non-stationary noises and…

Computation and Language · Computer Science 2017-03-24 Mirco Ravanelli , Philemon Brakel , Maurizio Omologo , Yoshua Bengio

It has become mainstream in computer vision and other machine learning domains to reuse backbone networks pre-trained on large datasets as preprocessors. Typically, the last layer is replaced by a shallow learning machine of sorts; the…

Machine Learning · Computer Science 2023-10-03 Haozhe Sun , Isabelle Guyon , Felix Mohr , Hedi Tabia

We present a network architecture for processing point clouds that directly operates on a collection of points represented as a sparse set of samples in a high-dimensional lattice. Naively applying convolutions on this lattice scales…

Computer Vision and Pattern Recognition · Computer Science 2018-05-10 Hang Su , Varun Jampani , Deqing Sun , Subhransu Maji , Evangelos Kalogerakis , Ming-Hsuan Yang , Jan Kautz

Training task in classical machine learning models, such as deep neural networks, is generally implemented at a remote cloud center for centralized learning, which is typically time-consuming and resource-hungry. It also incurs serious…

Machine Learning · Computer Science 2020-10-27 Jinke Ren , Guanding Yu , Guangyao Ding

In the field of deep learning, researchers often focus on inventing novel neural network models and improving benchmarks. In contrast, application developers are interested in making models suitable for actual products, which involves…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-15 Masao Someki , Yosuke Higuchi , Tomoki Hayashi , Shinji Watanabe

We present the first public release of our generic neural network training algorithm, called SkyNet. This efficient and robust machine learning tool is able to train large and deep feed-forward neural networks, including autoencoders, for…

Instrumentation and Methods for Astrophysics · Physics 2015-06-17 Philip Graff , Farhan Feroz , Michael P. Hobson , Anthony N. Lasenby

EfficientNets are a family of state-of-the-art image classification models based on efficiently scaled convolutional neural networks. Currently, EfficientNets can take on the order of days to train; for example, training an EfficientNet-B0…

Machine Learning · Computer Science 2020-11-06 Arissa Wongpanich , Hieu Pham , James Demmel , Mingxing Tan , Quoc Le , Yang You , Sameer Kumar

Multi-scale features are essential for dense prediction tasks, such as object detection, instance segmentation, and semantic segmentation. The prevailing methods usually utilize a classification backbone to extract multi-scale features and…

Computer Vision and Pattern Recognition · Computer Science 2023-11-01 Gang Zhang , Ziyi Li , Chufeng Tang , Jianmin Li , Xiaolin Hu

There has been a strong demand for algorithms that can execute machine learning as faster as possible and the speed of deep learning has accelerated by 30 times only in the past two years. Distributed deep learning using the large…

Learning algorithms for Deep Neural Networks are typically based on supervised end-to-end Stochastic Gradient Descent (SGD) training with error backpropagation (backprop). Backprop algorithms require a large number of labelled training…

Computer Vision and Pattern Recognition · Computer Science 2022-07-08 Gabriele Lagani , Claudio Gennaro , Hannes Fassold , Giuseppe Amato

Despite significant progress of deep learning in recent years, state-of-the-art semantic matching methods still rely on legacy features such as SIFT or HoG. We argue that the strong invariance properties that are key to the success of…

Computer Vision and Pattern Recognition · Computer Science 2017-04-18 David Novotny , Diane Larlus , Andrea Vedaldi

We rigorously evaluate three state-of-the-art techniques for inducing sparsity in deep neural networks on two large-scale learning tasks: Transformer trained on WMT 2014 English-to-German, and ResNet-50 trained on ImageNet. Across thousands…

Machine Learning · Computer Science 2019-02-27 Trevor Gale , Erich Elsen , Sara Hooker

With the rapid development of deep learning, a growing number of pre-trained models have been publicly available. However, deploying these fixed models in real-world IoT applications is challenging because different devices possess…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Maoyu Wang , Yao Lu , Jiaqi Nie , Zeyu Wang , Yun Lin , Qi Xuan , Guan Gui

Multivariate time series forecasting is an important machine learning problem across many domains, including predictions of solar plant energy output, electricity consumption, and traffic jam situation. Temporal data arise in these…

Machine Learning · Computer Science 2018-04-20 Guokun Lai , Wei-Cheng Chang , Yiming Yang , Hanxiao Liu