English
Related papers

Related papers: Expanded Gating Ranges Improve Activation Function…

200 papers

The choice of activation functions is crucial for modern deep neural networks. Popular hand-designed activation functions like Rectified Linear Unit(ReLU) and its variants show promising performance in various tasks and models. Swish, the…

Computer Vision and Pattern Recognition · Computer Science 2021-04-09 Yucong Zhou , Zezhou Zhu , Zhao Zhong

Activation functions play a crucial role in neural networks because they are the nonlinearities which have been attributed to the success story of deep learning. One of the currently most popular activation functions is ReLU, but several…

Computation and Language · Computer Science 2019-01-10 Steffen Eger , Paul Youssef , Iryna Gurevych

Gated Linear Units (GLU) have shown great potential in enhancing neural network performance. In this paper, I introduce a novel attention mechanism called GLU Attention, which introduces nonlinearity into the values of Attention. My…

Machine Learning · Computer Science 2025-07-08 Zehao Wang

We propose a novel high-performance, interpretable, and parameter \& computationally efficient deep learning architecture for tabular data, Gated Adaptive Network for Deep Automated Learning of Features (GANDALF). GANDALF relies on a new…

Machine Learning · Computer Science 2024-01-11 Manu Joseph , Harsh Raj

We analyze a simple one-hidden-layer neural network with ReLU activation functions and fixed biases, with one-dimensional input and output. We study both continuous and discrete versions of the model, and we rigorously prove the convergence…

Machine Learning · Computer Science 2026-04-10 Fabricio Macià , Shu Nakamura

In the era of Deep Neural Network based solutions for a variety of real-life tasks, having a compact and energy-efficient deployable model has become fairly important. Most of the existing deep architectures use Rectifier Linear Unit (ReLU)…

Machine Learning · Computer Science 2022-06-02 Nancy Nayak , Sheetal Kalyani

Large Language Models (LLMs) with billions of parameters have drastically transformed AI applications. However, their demanding computation during inference has raised significant challenges for deployment on resource-constrained devices.…

Graph Neural Networks (GNNs) have achieved remarkable success by extending traditional convolution to learning on non-Euclidean data. The key to the GNNs is adopting the neural message-passing paradigm with two stages: aggregation and…

Machine Learning · Computer Science 2022-02-15 Yifei Zhang , Hao Zhu , Ziqiao Meng , Piotr Koniusz , Irwin King

We study the numerical and Boolean expressiveness of MPLang, a declarative language that captures the computation of graph neural networks (GNNs) through linear message passing and activation functions. We begin with A-MPLang, the fragment…

Machine Learning · Computer Science 2026-05-27 Pablo Barceló , Floris Geerts , Matthias Lanzinger , Klara Pakhomenko , Jan Van den Bussche

In this paper, we introduce "Power Linear Unit" (PoLU) which increases the nonlinearity capacity of a neural network and thus helps improving its performance. PoLU adopts several advantages of previously proposed activation functions.…

Machine Learning · Computer Science 2018-02-02 Yikang Li , Pak Lun Kevin Ding , Baoxin Li

The reason behind CNNs capability to learn high-dimensional complex features from the images is the non-linearity introduced by the activation function. Several advanced activation functions have been discovered to improve the training…

Machine Learning · Computer Science 2022-11-15 Jeevanshi Sharma

Activation functions (AFs) are crucial components of deep neural networks (DNNs), having a significant impact on their performance. An activation function in a DNN is typically a smooth, nonlinear function that transforms an input signal…

Machine Learning · Computer Science 2023-10-13 Stamatis Mastromichalakis

The efficacy of deep learning models has been called into question by the presence of adversarial examples. Addressing the vulnerability of deep learning models to adversarial examples is crucial for ensuring their continued development and…

Machine Learning · Computer Science 2024-05-08 Korn Sooksatra , Greg Hamerly , Pablo Rivas

Activation functions shape the outputs of artificial neurons and, therefore, are integral parts of neural networks in general and deep learning in particular. Some activation functions, such as logistic and relu, have been used for many…

Machine Learning · Computer Science 2021-01-26 Johannes Lederer

The success of artificial neural networks (ANNs) hinges greatly on the judicious selection of an activation function, introducing non-linearity into network and enabling them to model sophisticated relationships in data. However, the search…

Machine Learning · Computer Science 2024-05-24 Haoyuan Sun , Zihao Wu , Bo Xia , Pu Chang , Zibin Dong , Yifu Yuan , Yongzhe Chang , Xueqian Wang

An appropriate choice of the activation function (like ReLU, sigmoid or swish) plays an important role in the performance of (deep) multilayer perceptrons (MLP) for classification and regression learning. Prototype-based classification…

Machine Learning · Computer Science 2019-01-21 Thomas Villmann , John Ravichandran , Andrea Villmann , David Nebel , Marika Kaden

We present a unified representation of the most popular neural network activation functions. Adopting Mittag-Leffler functions of fractional calculus, we propose a flexible and compact functional form that is able to interpolate between…

Machine Learning · Computer Science 2024-10-10 Mohammad Mostafanejad

Activation functions have been shown to affect the performance of deep neural networks significantly. While the Rectified Linear Unit (ReLU) remains the dominant choice in practice, the optimal activation function for deep neural networks…

Machine Learning · Computer Science 2025-07-29 John Chidiac , Danielle Azar

Modeling sophisticated activation functions within deep learning architectures has evolved into a distinct research direction. Functions such as GELU, SELU, and SiLU offer smooth gradients and improved convergence properties, making them…

Current research suggests that the key factors in designing neural network architectures involve choosing number of filters for every convolution layer, number of hidden neurons for every fully connected layer, dropout and pruning. The…

Machine Learning · Computer Science 2020-09-17 Himanshu Pradeep Aswani , Amit Sethi
‹ Prev 1 3 4 5 6 7 10 Next ›