12/16/24, 3:09 PM Sigmoid function - Wikipedia

Sigmoid function
A sigmoid function is any mathematical
function whose graph has a characteristic S-
shaped or sigmoid curve.

A common example of a sigmoid function is the

logistic function, which is defined by the
formula:[1]

The logistic curve

Plot of the error function

Other sigmoid functions are given in the Examples section. In some fields, most notably in the
context of artificial neural networks, the term "sigmoid function" is used as a synonym for "logistic
function".

Special cases of the sigmoid function include the Gompertz curve (used in modeling systems that
saturate at large values of x) and the ogee curve (used in the spillway of some dams). Sigmoid
functions have domain of all real numbers, with return (response) value commonly monotonically
increasing but could be decreasing. Sigmoid functions most often show a return value (y axis) in
the range 0 to 1. Another commonly used range is from −1 to 1.

https://en.wikipedia.org/wiki/Sigmoid_function 1/6
12/16/24, 3:09 PM Sigmoid function - Wikipedia

A wide variety of sigmoid functions including the logistic and hyperbolic tangent functions have
been used as the activation function of artificial neurons. Sigmoid curves are also common in
statistics as cumulative distribution functions (which go from 0 to 1), such as the integrals of the
logistic density, the normal density, and Student's t probability density functions. The logistic
sigmoid function is invertible, and its inverse is the logit function.

Definition
A sigmoid function is a bounded, differentiable, real function that is defined for all real input
values and has a non-negative derivative at each point[1] [2] and exactly one inflection point.

Properties
In general, a sigmoid function is monotonic, and has a first derivative which is bell shaped.
Conversely, the integral of any continuous, non-negative, bell-shaped function (with one local
maximum and no local minimum, unless degenerate) will be sigmoidal. Thus the cumulative
distribution functions for many common probability distributions are sigmoidal. One such
example is the error function, which is related to the cumulative distribution function of a normal
distribution; another is the arctan function, which is related to the cumulative distribution
function of a Cauchy distribution.

A sigmoid function is constrained by a pair of horizontal asymptotes as .

A sigmoid function is convex for values less than a particular point, and it is concave for values
greater than that point: in many of the examples here, that point is 0.

Examples
Logistic function

Hyperbolic tangent (shifted and scaled

version of the logistic function, above)

Some sigmoid functions compared. In the drawing all

Arctangent function functions are normalized in such a way that their
slope at the origin is 1.

Gudermannian function

https://en.wikipedia.org/wiki/Sigmoid_function 2/6
12/16/24, 3:09 PM Sigmoid function - Wikipedia

Error function

Generalised logistic function

Smoothstep function

Some algebraic functions, for example

and in a more general form[3]

Up to shifts and scaling, many sigmoids are special cases of

where

is the inverse of the negative Box–Cox transformation, and and are shape
parameters.[4]
Smooth transition function[5] normalized to (-1,1):

using the hyperbolic tangent mentioned above. Here, is a free parameter encoding the slope at
, which must be greater than or equal to because any smaller value will result in a
function with multiple inflection points, which is therefore not a true sigmoid. This function is

https://en.wikipedia.org/wiki/Sigmoid_function 3/6
12/16/24, 3:09 PM Sigmoid function - Wikipedia

unusual because it actually attains the limiting values of -1 and 1 within a finite range, meaning
that its value is constant at -1 for all and at 1 for all . Nonetheless, it is smooth
(infinitely differentiable, ) everywhere, including at .

Applications
Many natural processes, such as those of
complex system learning curves, exhibit a
progression from small beginnings that
accelerates and approaches a climax over time.
When a specific mathematical model is lacking, a
sigmoid function is often used.[6]

The van Genuchten–Gupta model is based on an

inverted S-curve and applied to the response of
crop yield to soil salinity.

Examples of the application of the logistic S-

curve to the response of crop yield (wheat) to Inverted logistic S-curve to model the relation
both the soil salinity and depth to water table in between wheat yield and soil salinity
the soil are shown in modeling crop response in
agriculture.

In artificial neural networks, sometimes non-smooth functions are used instead for efficiency;
these are known as hard sigmoids.

In audio signal processing, sigmoid functions are used as waveshaper transfer functions to emulate
the sound of analog circuitry clipping.[7]

In biochemistry and pharmacology, the Hill and Hill–Langmuir equations are sigmoid functions.

In computer graphics and real-time rendering, some of the sigmoid functions are used to blend
colors or geometry between two values, smoothly and without visible seams or discontinuities.

Titration curves between strong acids and strong bases have a sigmoid shape due to the
logarithmic nature of the pH scale.

The logistic function can be calculated efficiently by utilizing type III Unums.[8]

See also
Step function – Linear combination of indicator functions of real intervals
Sign function – Mathematical function returning -1, 0 or 1
Heaviside step function – Indicator function of positive numbers
Logistic regression – Statistical model for a binary dependent variable
Logit – Function in statistics
Softplus function – Type of activation function
Soboleva modified hyperbolic tangent – Mathematical activation function in data analysis

https://en.wikipedia.org/wiki/Sigmoid_function 4/6
12/16/24, 3:09 PM Sigmoid function - Wikipedia

Softmax function – Smooth approximation of one-hot arg max

Swish function – Mathematical activation function in data analysis
Weibull distribution – Continuous probability distribution
Fermi–Dirac statistics – Statistical description for the behavior of fermions

References
1. Han, Jun; Morag, Claudio (1995). "The influence of the sigmoid function parameters on the
speed of backpropagation learning" (https://archive.org/details/fromnaturaltoart1995inte/page/1
95). In Mira, José; Sandoval, Francisco (eds.). From Natural to Artificial Neural Computation.
Lecture Notes in Computer Science. Vol. 930. pp. 195–201 (https://archive.org/details/fromnatu
raltoart1995inte/page/195). doi:10.1007/3-540-59497-3_175 (https://doi.org/10.1007%2F3-540-
59497-3_175). ISBN 978-3-540-59497-0.
2. Ling, Yibei; He, Bin (December 1993). "Entropic analysis of biological growth models" (https://ie
eexplore.ieee.org/document/250574). IEEE Transactions on Biomedical Engineering. 40 (12):
1193–2000. doi:10.1109/10.250574 (https://doi.org/10.1109%2F10.250574). PMID 8125495 (ht
tps://pubmed.ncbi.nlm.nih.gov/8125495).
3. Dunning, Andrew J.; Kensler, Jennifer; Coudeville, Laurent; Bailleux, Fabrice (2015-12-28).
"Some extensions in continuous methods for immunological correlates of protection" (https://w
ww.ncbi.nlm.nih.gov/pmc/articles/PMC4692073). BMC Medical Research Methodology. 15
(107): 107. doi:10.1186/s12874-015-0096-9 (https://doi.org/10.1186%2Fs12874-015-0096-9).
PMC 4692073 (https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4692073). PMID 26707389 (http
s://pubmed.ncbi.nlm.nih.gov/26707389).
4. "grex --- Growth-curve Explorer" (https://github.com/ogarciav/grex). GitHub. 2022-07-09.
Archived (https://web.archive.org/web/20220825202325/https://github.com/ogarciav/grex) from
the original on 2022-08-25. Retrieved 2022-08-25.
5. EpsilonDelta (2022-08-16). "Smooth Transition Function in One Dimension | Smooth Transition
Function Series Part 1" (https://www.youtube.com/watch?v=vD5g8aVscUI). 13:29/14:04 – via
www.youtube.com.
6. Gibbs, Mark N.; Mackay, D. (November 2000). "Variational Gaussian process classifiers". IEEE
Transactions on Neural Networks. 11 (6): 1458–1464. doi:10.1109/72.883477 (https://doi.org/1
0.1109%2F72.883477). PMID 18249869 (https://pubmed.ncbi.nlm.nih.gov/18249869).
S2CID 14456885 (https://api.semanticscholar.org/CorpusID:14456885).
7. Smith, Julius O. (2010). Physical Audio Signal Processing (https://ccrma.stanford.edu/~jos/pas
p/Soft_Clipping.html) (2010 ed.). W3K Publishing. ISBN 978-0-9745607-2-4. Archived (https://
web.archive.org/web/20220714165138/https://ccrma.stanford.edu/~jos/pasp/Soft_Clipping.htm
l) from the original on 2022-07-14. Retrieved 2020-03-28.
8. Gustafson, John L.; Yonemoto, Isaac (2017-06-12). "Beating Floating Point at its Own Game:
Posit Arithmetic" (http://www.johngustafson.net/pdfs/BeatingFloatingPoint.pdf) (PDF). Archived
(https://web.archive.org/web/20220714164957/http://www.johngustafson.net/pdfs/BeatingFloati
ngPoint.pdf) (PDF) from the original on 2022-07-14. Retrieved 2019-12-28.

Further reading
Mitchell, Tom M. (1997). Machine Learning. WCB McGraw–Hill. ISBN 978-0-07-042807-2..
(NB. In particular see "Chapter 4: Artificial Neural Networks" (in particular pp. 96–97) where
Mitchell uses the word "logistic function" and the "sigmoid function" synonymously – this
function he also calls the "squashing function" – and the sigmoid (aka logistic) function is used
to compress the outputs of the "neurons" in multi-layer neural nets.)
Humphrys, Mark. "Continuous output, the sigmoid function" (http://www.computing.dcu.ie/~hum
phrys/Notes/Neural/sigmoid.html). Archived (https://web.archive.org/web/20220714165249/http
s://humphryscomputing.com/Notes/Neural/sigmoid.html) from the original on 2022-07-14.

https://en.wikipedia.org/wiki/Sigmoid_function 5/6
12/16/24, 3:09 PM Sigmoid function - Wikipedia

Retrieved 2022-07-14. (NB. Properties of the sigmoid, including how it can shift along axes and
how its domain may be transformed.)

External links
"Fitting of logistic S-curves (sigmoids) to data using SegRegA" (https://www.waterlog.info/sigm
oid.htm). Archived (https://web.archive.org/web/20220714181630/https://www.waterlog.info/sig
moid.htm) from the original on 2022-07-14.

Retrieved from "https://en.wikipedia.org/w/index.php?title=Sigmoid_function&oldid=1261826297"

https://en.wikipedia.org/wiki/Sigmoid_function 6/6