English
Related papers

Related papers: Expanded Gating Ranges Improve Activation Function…

200 papers

Recently, self-normalizing neural networks (SNNs) have been proposed with the intention to avoid batch or weight normalization. The key step in SNNs is to properly scale the exponential linear unit (referred to as SELU) to inherently…

Machine Learning · Computer Science 2018-07-30 G. Zhang , H. Li

Deep neural networks paved the way for significant improvements in image visual categorization during the last years. However, even though the tasks are highly varying, differing in complexity and difficulty, existing solutions mostly build…

Machine Learning · Computer Science 2019-10-29 Mina Basirat , Peter M. Roth

Lipschitz-constrained neural networks have many applications in machine learning. Since designing and training expressive Lipschitz-constrained networks is very challenging, there is a need for improved methods and a better theoretical…

Machine Learning · Computer Science 2022-04-14 Sebastian Neumayer , Alexis Goujon , Pakshal Bohra , Michael Unser

It is well-known that overparametrized neural networks trained using gradient-based methods quickly achieve small training error with appropriate hyperparameter settings. Recent papers have proved this statement theoretically for highly…

Machine Learning · Computer Science 2020-04-13 Abhishek Panigrahi , Abhishek Shetty , Navin Goyal

Activation functions play a pivotal role in the function learning using neural networks. The non-linearity in the learned function is achieved by repeated use of the activation function. Over the years, numerous activation functions have…

Machine Learning · Computer Science 2020-10-13 Koushik Biswas , Sandeep Kumar , Shilpak Banerjee , Ashish Kumar Pandey

Activation functions have a notorious impact on neural networks on both training and testing the models against the desired problem. Currently, the most used activation function is the Rectified Linear Unit (ReLU). This paper introduces a…

Computer Vision and Pattern Recognition · Computer Science 2018-01-23 Eric Alcaide

Recently, neural networks have been widely applied in the power system area. They can be used for better predicting input information and modeling system performance with increased accuracy. In some applications such as battery degradation…

Machine Learning · Computer Science 2025-05-27 Cunzhi Zhao , Fan Jiang , Xingpeng Li

Gradient-only line searches (GOLS) adaptively determine step sizes along search directions for discontinuous loss functions resulting from dynamic mini-batch sub-sampling in neural network training. Step sizes in GOLS are determined by…

Machine Learning · Statistics 2020-02-25 D. Kafka , Daniel. N. Wilke

In this paper, we have extended the well-established universal approximator theory to neural networks that use the unbounded ReLU activation function and a nonlinear softmax output layer. We have proved that a sufficiently large neural…

Machine Learning · Computer Science 2020-02-12 Behnam Asadi , Hui Jiang

Real world recommendation systems influence a constantly growing set of domains. With deep networks, that now drive such systems, recommendations have been more relevant to the user's interests and tasks. However, they may not always be…

Machine Learning · Computer Science 2022-02-15 Gil I. Shamir , Dong Lin

This paper demonstrates that a single-layer neural network using Parametric Rectified Linear Unit (PReLU) activation can solve the XOR problem, a simple fact that has been overlooked so far. We compare this solution to the multi-layer…

Neural and Evolutionary Computing · Computer Science 2024-09-18 Rafael C. Pinto , Anderson R. Tavares

Understanding the asymptotic behavior of gradient-descent training of deep neural networks is essential for revealing inductive biases and improving network performance. We derive the infinite-time training limit of a mathematically…

Machine Learning · Statistics 2022-02-08 Samuel Lippl , L. F. Abbott , SueYeon Chung

We provide a convergence analysis of gradient descent for the problem of agnostically learning a single ReLU function with moderate bias under Gaussian distributions. Unlike prior work that studies the setting of zero bias, we consider the…

Machine Learning · Computer Science 2024-11-05 Pranjal Awasthi , Alex Tang , Aravindan Vijayaraghavan

Many neural network architectures rely on the choice of the activation function for each hidden layer. Given the activation function, the neural network is trained over the bias and the weight parameters. The bias catches the center of the…

Machine Learning · Computer Science 2019-10-01 Farnoush Farhadi , Vahid Partovi Nia , Andrea Lodi

The training process of neural networks usually optimize weights and bias parameters of linear transformations, while nonlinear activation functions are pre-specified and fixed. This work develops a systematic approach to constructing…

Machine Learning · Computer Science 2024-10-29 Zhengqi Liu , Shuhao Cao , Yuwen Li , Ludmil Zikatanov

We establish that randomly initialized neural networks, with large width and a natural choice of hyperparameters, have nearly independent outputs exactly when their activation function is nonlinear with zero mean under the Gaussian measure:…

Machine Learning · Computer Science 2026-01-13 John Dunbar , Scott Aaronson

This paper proposes $\mathrm{dynActivation}$, a per-layer trainable activation defined as $f_i(x) = \mathrm{BaseAct}(x)(\alpha_i - \beta_i) + \beta_i x$, where $\alpha_i$ and $\beta_i$ are lightweight learned scalars that interpolate…

Machine Learning · Computer Science 2026-03-24 Alois Bachmann

Active learning methods aim to improve sample complexity in machine learning. In this work, we investigate an active learning scheme via a novel gradient-free cutting-plane training method for ReLU networks of arbitrary depth and develop a…

Machine Learning · Computer Science 2025-06-26 Erica Zhang , Fangzhao Zhang , Mert Pilanci

Gated recurrent neural networks have achieved remarkable results in the analysis of sequential data. Inside these networks, gates are used to control the flow of information, allowing to model even very long-term dependencies in the data.…

Neural and Evolutionary Computing · Computer Science 2018-07-12 Simone Scardapane , Steven Van Vaerenbergh , Danilo Comminiello , Simone Totaro , Aurelio Uncini

Transformers have improved drastically the performance of natural language processing (NLP) and computer vision applications. The computation of transformers involves matrix multiplications and non-linear activation functions such as…

Hardware Architecture · Computer Science 2024-02-19 Christodoulos Peltekis , Kosmas Alexandridis , Giorgos Dimitrakopoulos