Skip to search formSkip to main contentSkip to account menu

Rectifier (neural networks)

Known as: RELU, Rectifier (disambiguation), Softplus 
In the context of artificial neural networks, the rectifier is an activation function defined as where x is the input to a neuron. This is also known… 
Wikipedia (opens in a new tab)

Related topics

Related topics

18 relations
Activation functionArtificial neural networkBackpropagationComputer vision

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
Highly Cited
2019
Highly Cited
2019
U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
We propose a novel method for unsupervised image-to-image translation, which incorporates a new attention module and a new… 
Highly Cited
2018
Highly Cited
2018
Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm
In this work, we study the 1-bit convolutional neural networks (CNNs), of which both the weights and activations are binary… 
Highly Cited
2018
Highly Cited
2018
Towards Fast Computation of Certified Robustness for ReLU Networks
Verifying the robustness property of a general Rectified Linear Unit (ReLU) network is an NP-complete problem [Katz, Barrett… 
Highly Cited
2017
Highly Cited
2017
The Expressive Power of Neural Networks: A View from the Width
The expressive power of neural networks is important for understanding deep learning. Most existing works consider this problem… 
Highly Cited
2017
Highly Cited
2017
Swish: a Self-Gated Activation Function
The choice of activation functions in deep networks has a significant effect on the training dynamics and task performance… 
Highly Cited
2016
Highly Cited
2016
Why Deep Neural Networks for Function Approximation?
Recently there has been much interest in understanding why deep neural networks are preferred to shallow networks. We show that… 
Highly Cited
2016
Highly Cited
2016
Understanding Deep Neural Networks with Rectified Linear Units
In this paper we investigate the family of functions representable by deep neural networks (DNN) with rectified linear units… 
Highly Cited
2016
Highly Cited
2016
Convolutional Rectifier Networks as Generalized Tensor Decompositions
Convolutional rectifier networks, i.e. convolutional neural networks with rectified linear activation and max or average pooling… 
Highly Cited
1988
Highly Cited
1988
Satellite radar interferometry: Two-dimensional phase unwrapping
Interferometric synthetic aperture radar observations provide a means for obtaining high-resolution digital topographic maps from… 
Highly Cited
1963
Highly Cited
1963
SERIES RESISTANCE EFFECTS ON SOLAR CELL MEASUREMENTS
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)