English
Related papers

Related papers: Shifting Mean Activation Towards Zero with Bipolar…

200 papers

Recent theoretical work has demonstrated that deep neural networks have superior performance over shallow networks, but their training is more difficult, e.g., they suffer from the vanishing gradient problem. This problem can be typically…

Machine Learning · Statistics 2021-11-03 Lu Lu , Yanhui Su , George Em Karniadakis

This paper explores the expressive power of deep neural networks for a diverse range of activation functions. An activation function set $\mathscr{A}$ is defined to encompass the majority of commonly used activation functions, such as…

Machine Learning · Computer Science 2024-02-28 Shijun Zhang , Jianfeng Lu , Hongkai Zhao

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

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

We develop exact representations of training two-layer neural networks with rectified linear units (ReLUs) in terms of a single convex program with number of variables polynomial in the number of training samples and the number of hidden…

Machine Learning · Computer Science 2020-08-18 Mert Pilanci , Tolga Ergen

Activation function is crucial to the recent successes of deep neural networks. In this paper, we first propose a new activation function, Multiple Parametric Exponential Linear Units (MPELU), aiming to generalize and unify the rectified…

Computer Vision and Pattern Recognition · Computer Science 2017-01-18 Yang Li , Chunxiao Fan , Yong Li , Qiong Wu , Yue Ming

Fourier Analysis Network (FAN) was recently proposed as a simple way to improve neural network performance by replacing part of Rectified Linear Unit (ReLU) activations with sine and cosine functions. Although several studies have reported…

Machine Learning · Computer Science 2026-03-16 Sam Jeong , Hae Yong Kim

The success of deep networks has been attributed in part to their expressivity: per parameter, deep networks can approximate a richer class of functions than shallow networks. In ReLU networks, the number of activation patterns is one…

Machine Learning · Statistics 2019-10-22 Boris Hanin , David Rolnick

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

In this work, we provide a characterization of the feature-learning process in two-layer ReLU networks trained by gradient descent on the logistic loss following random initialization. We consider data with binary labels that are generated…

Machine Learning · Computer Science 2023-09-15 Spencer Frei , Niladri S. Chatterji , Peter L. Bartlett

This work provides a thorough study on how reward scaling can affect performance of deep reinforcement learning agents. In particular, we would like to answer the question that how does reward scaling affect non-saturating ReLU networks in…

Machine Learning · Computer Science 2018-11-01 Yueh-Hua Wu , Fan-Yun Sun , Yen-Yu Chang , Shou-De Lin

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 the data. In this…

Computer Vision and Pattern Recognition · Computer Science 2021-12-20 Haigen Hu , Aizhu Liu , Qiu Guan , Xiaoxin Li , Shengyong Chen , Qianwei Zhou

The loss function used to train a neural network is strongly connected to its output layer from a statistical point of view. This technical report analyzes common activation functions for a neural network output layer, like linear, sigmoid,…

Machine Learning · Computer Science 2025-11-10 Fernando Berzal

Activation functions play a critical role in deep neural networks by shaping gradient flow, optimization stability, and generalization. While ReLU remains widely used due to its simplicity, it suffers from gradient sparsity and dead-neuron…

Machine Learning · Computer Science 2025-12-03 Ashkan Shakarami , Yousef Yeganeh , Azade Farshad , Lorenzo Nicolè , Stefano Ghidoni , Nassir Navab

This paper proposes a learnable nonlinear activation mechanism specifically for convolutional neural network (CNN) termed as LENI, which learns to enhance the negative information in CNNs. In sharp contrast to ReLU which cuts off the…

Computer Vision and Pattern Recognition · Computer Science 2023-06-21 Zhicheng Cai , Chenglei Peng , Qiu Shen

We analyze the dynamics of training deep ReLU networks and their implications on generalization capability. Using a teacher-student setting, we discovered a novel relationship between the gradient received by hidden student nodes and the…

Machine Learning · Computer Science 2019-07-01 Yuandong Tian , Tina Jiang , Qucheng Gong , Ari Morcos

Deep Learning has revolutionized vision via convolutional neural networks (CNNs) and natural language processing via recurrent neural networks (RNNs). However, success stories of Deep Learning with standard feed-forward neural networks…

Machine Learning · Computer Science 2018-01-31 Günter Klambauer , Thomas Unterthiner , Andreas Mayr , Sepp Hochreiter

There has been a growing interest in expressivity of deep neural networks. However, most of the existing work about this topic focuses only on the specific activation function such as ReLU or sigmoid. In this paper, we investigate the…

Machine Learning · Statistics 2019-07-24 Ilsang Ohn , Yongdai Kim

Deep feedforward neural networks with piecewise linear activations are currently producing the state-of-the-art results in several public datasets. The combination of deep learning models and piecewise linear activation functions allows for…

Computer Vision and Pattern Recognition · Computer Science 2015-11-03 Zhibin Liao , Gustavo Carneiro

An increasingly popular machine learning paradigm is to pretrain a neural network (NN) on many tasks offline, then adapt it to downstream tasks, often by re-training only the last linear layer of the network. This approach yields strong…

Machine Learning · Computer Science 2024-06-10 Liam Collins , Hamed Hassani , Mahdi Soltanolkotabi , Aryan Mokhtari , Sanjay Shakkottai