English
Related papers

Related papers: Optimized Weight Initialization on the Stiefel Man…

200 papers

Activation functions are critical components in deep neural networks, directly influencing gradient flow, training stability, and model performance. Traditional functions like ReLU suffer from dead neuron problems, while sigmoid and tanh…

Machine Learning · Computer Science 2025-07-31 Sergii Kavun

Overparameterized models may have many interpolating solutions; implicit regularization refers to the hidden preference of a particular optimization method towards a certain interpolating solution among the many. A by now established line…

Machine Learning · Computer Science 2024-09-18 Hung-Hsu Chou , Holger Rauhut , Rachel Ward

There is great interest in using formal methods to guarantee the reliability of deep neural networks. However, these techniques may also be used to implant carefully selected input-output pairs. We present initial results on a novel…

Machine Learning · Computer Science 2020-08-05 Ivan Papusha , Rosa Wu , Joshua Brulé , Yanni Kouskoulas , Daniel Genin , Aurora Schmidt

The choice of activation function can have a large effect on the performance of a neural network. While there have been some attempts to hand-engineer novel activation functions, the Rectified Linear Unit (ReLU) remains the most…

Machine Learning · Computer Science 2020-04-14 Garrett Bingham , William Macke , Risto Miikkulainen

The implicit bias induced by the training of neural networks has become a topic of rigorous study. In the limit of gradient flow and gradient descent with appropriate step size, it has been shown that when one trains a deep linear network…

Machine Learning · Computer Science 2022-04-27 Thien Le , Stefanie Jegelka

Activation functions have come up as one of the essential components of neural networks. The choice of adequate activation function can impact the accuracy of these methods. In this study, we experiment for finding an optimal activation…

Machine Learning · Computer Science 2022-02-25 Vipul Bansal

An interesting approach to analyzing neural networks that has received renewed attention is to examine the equivalent kernel of the neural network. This is based on the fact that a fully connected feedforward network with one hidden layer,…

Machine Learning · Computer Science 2018-06-04 Russell Tsuchida , Farbod Roosta-Khorasani , Marcus Gallagher

Activation functions are fundamental for enabling nonlinear representations in deep neural networks. However, the standard rectified linear unit (ReLU) often suffers from inactive or "dead" neurons caused by its hard zero cutoff. To address…

Machine Learning · Computer Science 2025-11-12 Md Motaleb Hossen Manik , Md Zabirul Islam , Ge Wang

Deep neural network (DNN) generally takes thousands of iterations to optimize via gradient descent and thus has a slow convergence. In addition, softmax, as a decision layer, may ignore the distribution information of the data during…

Machine Learning · Computer Science 2021-06-16 Rui Zhang , Ziheng Jiao , Hongyuan Zhang , Xuelong Li

Optimizing deep neural networks (DNNs) often suffers from the ill-conditioned problem. We observe that the scaling-based weight space symmetry property in rectified nonlinear network will cause this negative effect. Therefore, we propose to…

Machine Learning · Computer Science 2017-10-09 Lei Huang , Xianglong Liu , Bo Lang , Bo Li

We present a theoretical and empirical study of the gradient dynamics of overparameterized shallow ReLU networks with one-dimensional input, solving least-squares interpolation. We show that the gradient dynamics of such networks are…

Machine Learning · Computer Science 2019-06-20 Francis Williams , Matthew Trager , Claudio Silva , Daniele Panozzo , Denis Zorin , Joan Bruna

The large number of ReLU non-linearity operations in existing deep neural networks makes them ill-suited for latency-efficient private inference (PI). Existing techniques to reduce ReLU operations often involve manual effort and sacrifice…

Computer Vision and Pattern Recognition · Computer Science 2023-01-24 Souvik Kundu , Shunlin Lu , Yuke Zhang , Jacqueline Liu , Peter A. Beerel

The ability to train randomly initialised deep neural networks is known to depend strongly on the variance of the weight matrices and biases as well as the choice of nonlinear activation. Here we complement the existing geometric analysis…

Information Theory · Computer Science 2021-02-09 Jared Tanner , Giuseppe Ughi

Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon…

Machine Learning · Computer Science 2022-05-17 Hancheng Min , Salma Tarmoun , Rene Vidal , Enrique Mallada

ReLU, a commonly used activation function in deep neural networks, is prone to the issue of "Dying ReLU". Several enhanced versions, such as ELU, SeLU, and Swish, have been introduced and are considered to be less commonly utilized.…

Machine Learning · Computer Science 2024-07-12 Jamshaid Ul Rahman , Rubiqa Zulfiqar , Asad Khan , Nimra

We explore convergence of deep neural networks with the popular ReLU activation function, as the depth of the networks tends to infinity. To this end, we introduce the notion of activation domains and activation matrices of a ReLU network.…

Machine Learning · Computer Science 2023-01-11 Yuesheng Xu , Haizhang Zhang

Weight initialization significantly impacts the convergence and performance of neural networks. While traditional methods like Xavier and Kaiming initialization are widely used, they often fall short for spiking neural networks (SNNs),…

Machine Learning · Computer Science 2024-11-28 Da Chang , Deliang Wang , Xiao Yang

In this paper, we explore some basic questions on the complexity of training neural networks with ReLU activation function. We show that it is NP-hard to train a two-hidden layer feedforward ReLU neural network. If dimension of the input…

Computational Complexity · Computer Science 2020-11-05 Digvijay Boob , Santanu S. Dey , Guanghui Lan

In recent years, deep learning has made remarkable progress in a wide range of domains, with a particularly notable impact on natural language processing tasks. One of the challenges associated with training deep neural networks in the…

Machine Learning · Computer Science 2024-06-27 Hanna Mazzawi , Xavi Gonzalvo , Michael Wunder , Sammy Jerome , Benoit Dherin

Static sparse training aims to train sparse models from scratch, achieving remarkable results in recent years. A key design choice is given by the sparse initialization, which determines the trainable sub-network through a binary mask.…

Machine Learning · Computer Science 2024-06-05 Aleksandra Irena Nowak , Łukasz Gniecki , Filip Szatkowski , Jacek Tabor
‹ Prev 1 8 9 10 Next ›