Skip to search formSkip to main content
You are currently offline. Some features of the site may not work correctly.

Activation function

In computational networks, the activation function of a node defines the output of that node given an input or set of inputs. A standard computer… Expand
Wikipedia

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
Highly Cited
2018
Highly Cited
2018
The choice of activation functions in deep networks has a significant effect on the training dynamics and task performance… Expand
  • figure 1
  • figure 2
  • figure 3
  • table 2
  • figure 5
Is this relevant?
Highly Cited
2017
Highly Cited
2017
The choice of activation functions in deep networks has a significant effect on the training dynamics and task performance… Expand
  • figure 1
  • figure 2
  • figure 3
  • figure 4
  • figure 5
Is this relevant?
Highly Cited
2016
Highly Cited
2016
Common nonlinear activation functions used in neural networks can cause training difficulties due to the saturation behavior of… Expand
  • figure 1
  • figure 2
  • figure 3
  • figure 4
  • figure 6
Is this relevant?
Highly Cited
2015
Highly Cited
2015
In this paper we investigate the performance of different types of rectified activation functions in convolutional neural network… Expand
  • figure 1
  • table 2
  • table 1
  • table 3
  • table 4
Is this relevant?
Highly Cited
2015
Highly Cited
2015
Artificial neural networks typically have a fixed, non-linear activation function at each neuron. We have designed a novel form… Expand
  • figure 1
  • table 1
  • table 2
  • table 3
  • figure 2
Is this relevant?
Highly Cited
2011
Highly Cited
2011
The activation function used to transform the activation level of a unit (neuron) into an output signal. There are a number of… Expand
  • figure 2
  • figure 3
  • figure 4
  • figure 5
  • figure 6
Is this relevant?
Highly Cited
2010
Highly Cited
2010
In this study, new neural network models with adaptive activation function (NNAAF) were implemented to classify ECG arrhythmias… Expand
  • figure 1
  • figure 2
  • table 2
  • table 3
  • table 4
Is this relevant?
Highly Cited
1993
Highly Cited
1993
Several researchers characterized the activation function under which multilayer feedforwardnetworks can act as universal… Expand
Is this relevant?
Highly Cited
1993
Highly Cited
1993
An activation function, possibly new, is proposed for use in digital simulation of artiicial neural networks, on the ground that… Expand
Is this relevant?
1993
1993
We study the complexity problem in artificial feedforward neural networks designed to approximate real valued functions of… Expand
  • table 1
Is this relevant?