English
Related papers

Related papers: How Controlling the Variance can Improve Training …

200 papers

Recent works reveal that re-calibrating the intermediate activation of adversarial examples can improve the adversarial robustness of a CNN model. The state of the arts [Baiet al., 2021] and [Yanet al., 2021] explores this feature at the…

Computer Vision and Pattern Recognition · Computer Science 2022-02-25 Zhi-Yuan Zhang , Di Liu

Safety-critical technical systems operating in unknown environments require the ability to quickly adapt their behavior, which can be achieved in control by inferring a model online from the data stream generated during operation. Gaussian…

Systems and Control · Electrical Eng. & Systems 2022-02-24 Armin Lederer , Mingmin Zhang , Samuel Tesfazgi , Sandra Hirche

Deep neural networks (DNNs) are becoming increasingly deeper, wider, and non-linear due to the growing demands on prediction accuracy and analysis quality. When training a DNN model, the intermediate activation data must be saved in the…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-11-24 Sian Jin , Guanpeng Li , Shuaiwen Leon Song , Dingwen Tao

We propose and investigate new complementary methodologies for estimating predictive variance networks in regression neural networks. We derive a locally aware mini-batching scheme that result in sparse robust gradients, and show how to…

Machine Learning · Statistics 2019-11-05 Nicki S. Detlefsen , Martin Jørgensen , Søren Hauberg

Deep neural networks (DNNs) are powerful tools for compressing and distilling information. Their scale and complexity, often involving billions of inter-dependent parameters, render direct microscopic analysis difficult. Under such…

Machine Learning · Statistics 2022-09-26 Inbar Seroussi , Gadi Naveh , Zohar Ringel

In the machine learning domain, active learning is an iterative data selection algorithm for maximizing information acquisition and improving model performance with limited training samples. It is very useful, especially for the industrial…

Machine Learning · Statistics 2020-04-24 Xiaowei Yue , Yuchen Wen , Jeffrey H. Hunt , Jianjun Shi

Deep neural networks (DNNs) depend on the storage of a large number of parameters, which consumes an important portion of the energy used during inference. This paper considers the case where the energy usage of memory elements can be…

Machine Learning · Computer Science 2019-12-24 Sébastien Henwood , François Leduc-Primeau , Yvon Savaria

The typical training of neural networks using large stepsize gradient descent (GD) under the logistic loss often involves two distinct phases, where the empirical risk oscillates in the first phase but decreases monotonically in the second…

Machine Learning · Statistics 2024-06-28 Yuhang Cai , Jingfeng Wu , Song Mei , Michael Lindsey , Peter L. Bartlett

Training neural network models with discrete (categorical or structured) latent variables can be computationally challenging, due to the need for marginalization over large or combinatorial sets. To circumvent this issue, one typically…

Machine Learning · Computer Science 2020-12-29 Gonçalo M. Correia , Vlad Niculae , Wilker Aziz , André F. T. Martins

In modern deep learning, there is a recent and growing literature on the interplay between large-width asymptotic properties of deep Gaussian neural networks (NNs), i.e. deep NNs with Gaussian-distributed weights, and Gaussian stochastic…

Machine Learning · Computer Science 2022-06-27 Stefano Favaro , Sandra Fortini , Stefano Peluchetti

Neuroevolution is a promising area of research that combines evolutionary algorithms with neural networks. A popular subclass of neuroevolutionary methods, called evolution strategies, relies on dense noise perturbations to mutate networks,…

Neural and Evolutionary Computing · Computer Science 2023-02-14 Tim Whitaker , Darrell Whitley

In the past few years, neural networks have evolved from simple Feedforward Neural Networks to more complex neural networks, such as Convolutional Neural Networks and Recurrent Neural Networks. Where CNNs are a perfect fit for tasks where…

Machine Learning · Computer Science 2024-07-31 Harshil Darji

It is well known that artificial neural networks initialized from independent and identically distributed priors converge to Gaussian processes in the limit of a large number of neurons per hidden layer. In this work we prove an analogous…

Quantum Physics · Physics 2025-07-25 Diego García-Martín , Martin Larocca , M. Cerezo

Deep learning models tend to memorize training data, which hurts their ability to generalize to under-represented classes. We empirically study a convolutional neural network's internal representation of imbalanced image data and measure…

Machine Learning · Computer Science 2022-10-19 Damien Dablain , Colin Bellinger , Bartosz Krawczyk , Nitesh Chawla

We investigate deep Bayesian neural networks with Gaussian weight priors and a class of ReLU-like nonlinearities. Bayesian neural networks with Gaussian priors are well known to induce an L2, "weight decay", regularization. Our results…

Machine Learning · Statistics 2019-05-13 Mariia Vladimirova , Jakob Verbeek , Pablo Mesejo , Julyan Arbel

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh

Sparsification of neural networks is one of the effective complexity reduction methods to improve efficiency and generalizability. We consider the problem of learning a one hidden layer convolutional neural network with ReLU activation…

Optimization and Control · Mathematics 2020-02-26 Thu Dinh , Jack Xin

The training of graph neural networks (GNNs) is extremely time consuming because sparse graph-based operations are hard to be accelerated by hardware. Prior art explores trading off the computational precision to reduce the time complexity…

Machine Learning · Computer Science 2023-07-04 Zirui Liu , Shengyuan Chen , Kaixiong Zhou , Daochen Zha , Xiao Huang , Xia Hu

Deep learning has been wildly successful in practice and most state-of-the-art machine learning methods are based on neural networks. Lacking, however, is a rigorous mathematical theory that adequately explains the amazing performance of…

Machine Learning · Statistics 2023-10-03 Rahul Parhi , Robert D. Nowak

Training neural networks is an optimization problem, and finding a decent set of parameters through gradient descent can be a difficult task. A host of techniques has been developed to aid this process before and during the training phase.…

Machine Learning · Computer Science 2020-08-19 Divya Gaur , Joachim Folz , Andreas Dengel
‹ Prev 1 8 9 10 Next ›