English
Related papers

Related papers: Static Activation Function Normalization

200 papers

The paper briefy reviews several recent results on hierarchical architectures for learning from examples, that may formally explain the conditions under which Deep Convolutional Neural Networks perform much better in function approximation…

Machine Learning · Computer Science 2016-08-12 Hrushikesh Mhaskar , Tomaso Poggio

Batch Normalization (BatchNorm) is commonly used in Convolutional Neural Networks (CNNs) to improve training speed and stability. However, there is still limited consensus on why this technique is effective. This paper uses concepts from…

Neural and Evolutionary Computing · Computer Science 2021-06-02 Elaina Chai , Mert Pilanci , Boris Murmann

We explore the phase diagram of approximation rates for deep neural networks and prove several new theoretical results. In particular, we generalize the existing result on the existence of deep discontinuous phase in ReLU networks to…

Neural and Evolutionary Computing · Computer Science 2021-01-07 Dmitry Yarotsky , Anton Zhevnerchuk

We study the problem of training deep neural networks with Rectified Linear Unit (ReLU) activation function using gradient descent and stochastic gradient descent. In particular, we study the binary classification problem and show that for…

Machine Learning · Computer Science 2018-12-31 Difan Zou , Yuan Cao , Dongruo Zhou , Quanquan Gu

We present a simple, effective, and general activation function we term ACON which learns to activate the neurons or not. Interestingly, we find Swish, the recent popular NAS-searched activation, can be interpreted as a smooth approximation…

Computer Vision and Pattern Recognition · Computer Science 2021-04-19 Ningning Ma , Xiangyu Zhang , Ming Liu , Jian Sun

Batch Normalization (BatchNorm) is a widely adopted technique that enables faster and more stable training of deep neural networks (DNNs). Despite its pervasiveness, the exact reasons for BatchNorm's effectiveness are still poorly…

Machine Learning · Statistics 2019-04-16 Shibani Santurkar , Dimitris Tsipras , Andrew Ilyas , Aleksander Madry

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

Batch normalization is widely used in deep learning to normalize intermediate activations. Deep networks suffer from notoriously increased training complexity, mandating careful initialization of weights, requiring lower learning rates,…

Machine Learning · Statistics 2022-10-19 Lakshmi Annamalai , Chetan Singh Thakur

Adversarial training is an effective method to improve the machine learning (ML) model robustness. Most existing studies typically consider the Rectified linear unit (ReLU) activation function and centralized training environments. In this…

Machine Learning · Computer Science 2025-12-05 Long Dang , Thushari Hapuarachchi , Kaiqi Xiong , Jing Lin

Normalization techniques such as Batch Normalization have been applied successfully for training deep neural networks. Yet, despite its apparent empirical benefits, the reasons behind the success of Batch Normalization are mostly…

Machine Learning · Statistics 2018-10-09 Jonas Kohler , Hadi Daneshmand , Aurelien Lucchi , Ming Zhou , Klaus Neymeyr , Thomas Hofmann

We introduce SPLASH units, a class of learnable activation functions shown to simultaneously improve the accuracy of deep neural networks while also improving their robustness to adversarial attacks. SPLASH units have both a simple…

Machine Learning · Computer Science 2020-06-17 Mohammadamin Tavakoli , Forest Agostinelli , Pierre Baldi

Over the past few years, there has been a significant amount of research focused on studying the ReLU activation function, with the aim of achieving neural network convergence through over-parametrization. However, recent developments in…

Machine Learning · Computer Science 2023-03-30 Yeqi Gao , Sridhar Mahadevan , Zhao Song

Weight initialization is important for faster convergence and stability of deep neural networks training. In this paper, a robust initialization method is developed to address the training instability in long short-term memory (LSTM)…

The activation functions are fundamental to neural networks as they introduce non-linearity into data relationships, thereby enabling deep networks to approximate complex data relations. Existing efforts to enhance neural network…

Machine Learning · Computer Science 2024-09-26 Jiayu Li , Zilong Zhao , Kevin Yee , Uzair Javaid , Biplab Sikdar

Dropout and similar stochastic neural network regularization methods are often interpreted as implicitly averaging over a large ensemble of models. We propose STE (stochastically trained ensemble) layers, which enhance the averaging…

Machine Learning · Computer Science 2019-11-22 Alex Labach , Shahrokh Valaee

We analyze the dynamics of networks of spiking neural oscillators. First, we present an exact linear stability theory of the synchronous state for networks of arbitrary connectivity. For general neuron rise functions, stability is…

Neurons and Cognition · Quantitative Biology 2009-11-11 Marc Timme , Theo Geisel , Fred Wolf

In the last decade, an active area of research has been devoted to design novel activation functions that are able to help deep neural networks to converge, obtaining better performance. The training procedure of these architectures usually…

Machine Learning · Computer Science 2019-04-26 Franco Manessi , Alessandro Rozza

We present weight normalization: a reparameterization of the weight vectors in a neural network that decouples the length of those weight vectors from their direction. By reparameterizing the weights in this way we improve the conditioning…

Machine Learning · Computer Science 2016-06-07 Tim Salimans , Diederik P. Kingma

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

The activation function deployed in a deep neural network has great influence on the performance of the network at initialisation, which in turn has implications for training. In this paper we study how to avoid two problems at…

Machine Learning · Computer Science 2021-05-18 Michael Murray , Vinayak Abrol , Jared Tanner