中文
相关论文

相关论文: How Does Fourier Analysis Network Work? A Mechanis…

200 篇论文

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…

机器学习 · 计算机科学 2020-09-17 Himanshu Pradeep Aswani , Amit Sethi

This paper introduces a significantly better class of activation functions than the almost universally used ReLU like and Sigmoidal class of activation functions. Two new activation functions referred to as the Cone and Parabolic-Cone that…

人工智能 · 计算机科学 2024-05-08 Mathew Mithra Noel , Yug Oswal

This document proposes a parametric activation function (ac.f.) aimed at improving multidimensional nonlinear data regression. It is a established knowledge that nonlinear ac.f's are required for learning nonlinear datasets. This work shows…

机器学习 · 计算机科学 2025-10-03 Enda D. V. Bigarella

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.…

机器学习 · 计算机科学 2018-02-02 Yikang Li , Pak Lun Kevin Ding , Baoxin Li

Sparse Neural Networks (SNNs) can potentially demonstrate similar performance to their dense counterparts while saving significant energy and memory at inference. However, the accuracy drop incurred by SNNs, especially at high pruning…

机器学习 · 计算机科学 2023-06-06 Mohammad Loni , Aditya Mohan , Mehdi Asadi , Marius Lindauer

Rectified linear activation units are important components for state-of-the-art deep convolutional networks. In this paper, we propose a novel S-shaped rectified linear activation unit (SReLU) to learn both convex and non-convex functions,…

计算机视觉与模式识别 · 计算机科学 2015-12-23 Xiaojie Jin , Chunyan Xu , Jiashi Feng , Yunchao Wei , Junjun Xiong , Shuicheng Yan

We consider neural networks with rational activation functions. The choice of the nonlinear activation function in deep learning architectures is crucial and heavily impacts the performance of a neural network. We establish optimal bounds…

神经与进化计算 · 计算机科学 2020-10-01 Nicolas Boullé , Yuji Nakatsukasa , Alex Townsend

In this paper we investigate the performance of different types of rectified activation functions in convolutional neural network: standard rectified linear unit (ReLU), leaky rectified linear unit (Leaky ReLU), parametric rectified linear…

机器学习 · 计算机科学 2015-11-30 Bing Xu , Naiyan Wang , Tianqi Chen , Mu Li

Researchers have proposed various activation functions. These activation functions help the deep network to learn non-linear behavior with a significant effect on training dynamics and task performance. The performance of these activations…

计算机视觉与模式识别 · 计算机科学 2020-01-07 Pravendra Singh , Munender Varshney , Vinay P. Namboodiri

Deep neural networks can struggle to learn continually in the face of non-stationarity. This phenomenon is known as loss of plasticity. In this paper, we identify underlying principles that lead to plastic algorithms. In particular, we…

机器学习 · 计算机科学 2024-10-29 Alex Lewandowski , Dale Schuurmans , Marlos C. Machado

In recent years, deep neural networks (DNNs) achieved unprecedented performance in many low-level vision tasks. However, state-of-the-art results are typically achieved by very deep networks, which can reach tens of layers with tens of…

计算机视觉与模式识别 · 计算机科学 2018-03-28 Idan Kligvasser , Tamar Rott Shaham , Tomer Michaeli

This paper presents the double-activation neural network (DANN), a novel network architecture designed for solving parabolic equations with time delay. In DANN, each neuron is equipped with two activation functions to augment the network's…

数值分析 · 数学 2024-05-15 Qiumei Huang , Qiao Zhu

For most state-of-the-art architectures, Rectified Linear Unit (ReLU) becomes a standard component accompanied with each layer. Although ReLU can ease the network training to an extent, the character of blocking negative values may suppress…

计算机视觉与模式识别 · 计算机科学 2017-11-20 Xuanyi Dong , Guoliang Kang , Kun Zhan , Yi Yang

Activation functions are non-linearities in neural networks that allow them to learn complex mapping between inputs and outputs. Typical choices for activation functions are ReLU, Tanh, Sigmoid etc., where the choice generally depends on…

Artificial neural networks typically have a fixed, non-linear activation function at each neuron. We have designed a novel form of piecewise linear activation function that is learned independently for each neuron using gradient descent.…

神经与进化计算 · 计算机科学 2015-04-22 Forest Agostinelli , Matthew Hoffman , Peter Sadowski , Pierre Baldi

This study introduces a novel activation function, characterized by a dynamic slope that adjusts throughout the training process, aimed at enhancing adaptability and performance in deep neural networks for computer vision tasks. The…

计算机视觉与模式识别 · 计算机科学 2024-08-20 Archisman Chakraborti , Bidyut B Chaudhuri

Traditional Convolutional Neural Networks (CNNs) typically use the same activation function (usually ReLU) for all neurons with non-linear mapping operations. For example, the deep convolutional architecture Inception-v4 uses ReLU. To…

计算机视觉与模式识别 · 计算机科学 2018-05-31 Luna M. Zhang

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…

机器学习 · 计算机科学 2026-04-10 Fabricio Macià , Shu Nakamura

In the architecture of deep learning models, inspired by biological neurons, activation functions (AFs) play a pivotal role. They significantly influence the performance of artificial neural networks. By modulating the non-linear properties…

机器学习 · 计算机科学 2024-07-17 M. M. Hammad

Since stroke is the main cause of various cerebrovascular diseases, deep learning-based stroke lesion segmentation on magnetic resonance (MR) images has attracted considerable attention. However, the existing methods often neglect the…

图像与视频处理 · 电气工程与系统科学 2023-10-03 Weiyi Yu , Yiming Lei , Hongming Shan