Skip to search form
Skip to main content
Skip to account menu
Semantic Scholar
Semantic Scholar's Logo
Search 218,250,720 papers from all fields of science
Search
Sign In
Create Free Account
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
(opens in a new tab)
Create Alert
Alert
Related topics
Related topics
31 relations
Action potential
Artificial neural network
Artificial neuron
Autoencoder
Expand
Papers overview
Semantic Scholar uses AI to extract papers important to this topic.
Highly Cited
2016
Highly Cited
2016
Noisy Activation Functions
Çaglar Gülçehre
,
Marcin Moczulski
,
Misha Denil
,
Yoshua Bengio
International Conference on Machine Learning
2016
Corpus ID: 9198110
Common nonlinear activation functions used in neural networks can cause training difficulties due to the saturation behavior of…
Expand
Highly Cited
2005
Highly Cited
2005
Mechanistic models for the activation volume and rate sensitivity in metals with nanocrystalline grains and nano-scale twins
R. Asaro
,
S. Suresh
2005
Corpus ID: 6092129
Highly Cited
2001
Highly Cited
2001
Fast Electron Transfer Kinetics on Multiwalled Carbon Nanotube Microbundle Electrodes
J. M. Nugent
,
K. Santhanam
,
and A. Rubio
,
P. Ajayan
2001
Corpus ID: 73666467
The rate of electron transfer at carbon electrodes depends on various factors such as the structure and morphology of the carbon…
Expand
Highly Cited
2001
Highly Cited
2001
IKKα Provides an Essential Link between RANK Signaling and Cyclin D1 Expression during Mammary Gland Development
Yixue Cao
,
G. Bonizzi
,
+4 authors
M. Karin
Cell
2001
Corpus ID: 16951575
Highly Cited
1995
Highly Cited
1995
Simple kinetic models of petroleum formation. Part I : oil and gas generation from kerogen
A. Pepper
,
P. Corvi
1995
Corpus ID: 91178993
Highly Cited
1995
Highly Cited
1995
Monolayers in Three Dimensions: NMR, SAXS, Thermal, and Electron Hopping Studies of Alkanethiol Stabilized Gold Clusters
R. Terrill
,
T. Postlethwaite
,
+6 authors
G. Wignall
1995
Corpus ID: 42424227
Gold clusters stabilized by chemisorbed monolayers of octane-, dodecaneor hexadecanethiolate have been investigated in solution…
Expand
Highly Cited
1993
Highly Cited
1993
Substitution of three amino acids switches receptor specificity of Gqα to that of Giα
B. Conklin
,
Z. Farfel
,
K. Lustig
,
D. Julius
,
H. Bourne
Nature
1993
Corpus ID: 4350799
AGONIST-BOUND receptors activate heterotrimeric (αβγ) G proteins by catalysing replacement of GDP bound to the α-subunit by GTP1…
Expand
Highly Cited
1993
Highly Cited
1993
A Better Activation Function for Artificial Neural Networks
D. Elliott
1993
Corpus ID: 60842824
An activation function, possibly new, is proposed for use in digital simulation of artiicial neural networks, on the ground that…
Expand
Highly Cited
1993
Highly Cited
1993
How to Choose an Activation Function
H. Mhaskar
,
C. Micchelli
Neural Information Processing Systems
1993
Corpus ID: 2424388
We study the complexity problem in artificial feedforward neural networks designed to approximate real valued functions of…
Expand
Highly Cited
1989
Highly Cited
1989
Universal approximation using feedforward networks with non-sigmoid hidden layer activation functions
M. Stinchcombe
,
Halbert White
International Joint Conference on Neural…
1989
Corpus ID: 14470590
K.M. Hornik, M. Stinchcombe, and H. White (Univ. of California at San Diego, Dept. of Economics Discussion Paper, June 1988; to…
Expand
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)
ACCEPT & CONTINUE