paper-with-me

Papers

Nonlinearity Enhanced Adaptive Activation Functions

2024-03-29 · David Yevick

A general procedure for introducing parametric, learned, nonlinearity into activation functions is found to enhance the accuracy of representative neural networks without requiring significant additional computational resources. Examples are given based on the standard rectified linear unit (ReLU) as well as several other frequently employed activation functions. The associated accuracy improvement is quantified both in the context of the MNIST digit data set and a convolutional neural network (CNN) benchmark example.

📄 PDF Abstract BibTeX arXiv:2403.19896

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models

2024-11-06 · Zhijian Zhuo, Ya Wang, Yutao Zeng, XiaoQing Li 외

Transformers have found extensive applications across various domains due to the powerful fitting capabilities. This success can be partially attributed to their inherent nonlinearity. Thus, in addition to the ReLU funct…

Graph-Adaptive Activation Functions for Graph Neural Networks

2020-09-14 · Bianca Iancu, Luana Ruiz, Alejandro Ribeiro, Elvin Isufi

Activation functions are crucial in graph neural networks (GNNs) as they allow defining a nonlinear family of functions to capture the relationship between the input graph data and their representations. This paper propo…

Recommendation Systems

Adaptively Customizing Activation Functions for Various Layers

2021-12-17 · Haigen Hu, Aizhu Liu, Qiu Guan, Xiaoxin Li 외

To enhance the nonlinearity of neural networks and increase their mapping abilities between the inputs and response variables, activation functions play a crucial role to model more complex relationships and patterns in …

Competition-based Adaptive ReLU for Deep Neural Networks

2024-07-28 · Junjia Chen, Zhibin Pan

Activation functions introduce nonlinearity into deep neural networks. Most popular activation functions allow positive values to pass through while blocking or suppressing negative values. From the idea that positive va…

Blockingimage-classificationImage ClassificationSuper-Resolution

Padé Approximant Neural Networks for Enhanced Electric Motor Fault Diagnosis Using Vibration and Acoustic Data

2025-07-03 · Sertac Kilickaya, Levent Eren arxiv

Purpose: The primary aim of this study is to enhance fault diagnosis in induction machines by leveraging the Padé Approximant Neuron (PAON) model. While accelerometers and microphones are standard in motor condition moni…

Fault Diagnosis