English
Related papers

Related papers: Fractional moment-preserving initialization scheme…

200 papers

Traditional initialisation methods, e.g. He and Xavier, have been effective in avoiding the problem of vanishing or exploding gradients in neural networks. However, they only use simple pointwise distributions, which model one-dimensional…

Computer Vision and Pattern Recognition · Computer Science 2023-10-26 Christian Harder , Moritz Fuchs , Yuri Tolkach , Anirban Mukhopadhyay

Deep neural networks (DNNs) are state-of-the-art solutions for many machine learning applications, and have been widely used on mobile devices. Running DNNs on resource-constrained mobile devices often requires the help from edge servers…

Networking and Internet Architecture · Computer Science 2019-03-11 Wenqi Shi , Yunzhong Hou , Sheng Zhou , Zhisheng Niu , Yang Zhang , Lu Geng

Deploying deep neural networks (DNNs) in real-world environments poses challenges due to faults that can manifest in physical hardware from radiation, aging, and temperature fluctuations. To address this, previous works have focused on…

Machine Learning · Computer Science 2024-12-02 Ninnart Fuengfusin , Hakaru Tamukoh

Deep neural networks (DNNs) have been successfully applied to many real-world problems, but a complete understanding of their dynamical and computational principles is still lacking. Conventional theoretical frameworks for analysing DNNs…

Machine Learning · Computer Science 2022-03-25 Cheng Kevin Qu , Asem Wardak , Pulin Gong

We present an architecture of a recurrent neural network (RNN) with a fully-connected deep neural network (DNN) as its feature extractor. The RNN is equipped with both causal temporal prediction and non-causal look-ahead, via…

Machine Learning · Computer Science 2014-03-07 Jianshu Chen , Li Deng

Deep neural networks have achieved remarkable accomplishments in practice. The success of these networks hinges on effective initialization methods, which are vital for ensuring stable and rapid convergence during training. Recently,…

Machine Learning · Computer Science 2025-03-11 Yu Pan , Chaozheng Wang , Zekai Wu , Qifan Wang , Min Zhang , Zenglin Xu

Untrained large neural networks, just after random initialization, tend to favour a small subset of classes, assigning high predicted probabilities to these few classes and approximately zero probability to all others. This bias, termed…

Machine Learning · Computer Science 2025-11-27 Nicholas Pellegrino , David Szczecina , Paul W. Fieguth

Research aimed at scaling up neuroscience inspired learning algorithms for neural networks is accelerating. Recently, a key research area has been the study of energy-based learning algorithms such as predictive coding, due to their…

Machine Learning · Computer Science 2026-01-30 Luca Pinchetti , Simon Frieder , Thomas Lukasiewicz , Tommaso Salvatori

The weight initialization and the activation function of deep neural networks have a crucial impact on the performance of the training procedure. An inappropriate selection can lead to the loss of information of the input during forward…

Machine Learning · Statistics 2019-05-28 Soufiane Hayou , Arnaud Doucet , Judith Rousseau

Graph Neural Networks (GNNs) have demonstrated remarkable performance across a spectrum of graph-related tasks, however concerns persist regarding their vulnerability to adversarial perturbations. While prevailing defense strategies focus…

Machine Learning · Computer Science 2025-10-28 Sofiane Ennadir , Johannes F. Lutzeyer , Michalis Vazirgiannis , El Houcine Bergou

Using a mean-field theory of signal propagation, we analyze the evolution of correlations between two signals propagating forward through a deep ReLU network with correlated weights. Signals become highly correlated in deep ReLU networks…

Machine Learning · Computer Science 2021-05-26 Dayal Singh , G J Sreejith

Good weight initialization serves as an effective measure to reduce the training cost of a deep neural network (DNN) model. The choice of how to initialize parameters is challenging and may require manual tuning, which can be time-consuming…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Yifan Gong , Zheng Zhan , Yanyu Li , Yerlan Idelbayev , Andrey Zharkov , Kfir Aberman , Sergey Tulyakov , Yanzhi Wang , Jian Ren

To theoretically understand the behavior of trained deep neural networks, it is necessary to study the dynamics induced by gradient methods from a random initialization. However, the nonlinear and compositional structure of these models…

Machine Learning · Computer Science 2021-12-21 Karl Hajjar , Lénaïc Chizat , Christophe Giraud

Recent theoretical work has demonstrated that deep neural networks have superior performance over shallow networks, but their training is more difficult, e.g., they suffer from the vanishing gradient problem. This problem can be typically…

Machine Learning · Statistics 2021-11-03 Lu Lu , Yanhui Su , George Em Karniadakis

We propose an incremental training method that partitions the original network into sub-networks, which are then gradually incorporated in the running network during the training process. To allow for a smooth dynamic growth of the network,…

Machine Learning · Computer Science 2018-03-29 Roxana Istrate , Adelmo Cristiano Innocenza Malossi , Costas Bekas , Dimitrios Nikolopoulos

Despite the recent success of stochastic gradient descent in deep learning, it is often difficult to train a deep neural network with an inappropriate choice of its initial parameters. Even if training is successful, it has been known that…

Machine Learning · Computer Science 2023-02-10 Cheolhyoung Lee , Kyunghyun Cho

Randomly initialized neural networks induce a prior over functions, but the predictor used in practice is produced only after training. We ask how much of this initial bias survives the training pipeline. To make the question measurable, we…

Machine Learning · Computer Science 2026-05-29 Mohua Das , Pierfrancesco Beneventano , Shibshankar Dey , Gareth H. McKinkey , Tomaso Poggio

Initialization plays a critical role in the training of deep neural networks (DNN). Existing initialization strategies mainly focus on stabilizing the training process to mitigate gradient vanish/explosion problems. However, these…

Machine Learning · Computer Science 2021-08-17 Haitao Mao , Xu Chen , Qiang Fu , Lun Du , Shi Han , Dongmei Zhang

Deep neural networks are typically initialized with random weights, with variances chosen to facilitate signal propagation and stable gradients. It is also believed that diversity of features is an important property of these…

Machine Learning · Computer Science 2020-07-03 Yaniv Blumenfeld , Dar Gilboa , Daniel Soudry

When training data are limited, data-driven models are especially vulnerable to optimization-related fluctuations from random initialization and to sampling-induced bias from insufficient training data. We address both challenges with…

Nuclear Theory · Physics 2026-03-31 Yinu Zhang , Zhiyi Li , Kele Li , Jiaxuan Zhong , Cenxi Yuan