Soboleva modified hyperbolic tangent

Last updated

The Soboleva modified hyperbolic tangent, also known as (parametric) Soboleva modified hyperbolic tangent activation function ([P]SMHTAF), [nb 1] is a special S-shaped function based on the hyperbolic tangent, given by

Contents

EquationLeft tail controlRight tail control
SMHTAF 01.png
SMHTAF 02.png

History

This function was originally proposed as "modified hyperbolic tangent" [nb 1] by Ukrainian scientist Elena V. Soboleva (Елена В. Соболева) as a utility function for multi-objective optimization and choice modelling in decision-making. [1] [2] [3]

Practical usage

The function has since been introduced into neural network theory and practice. [4]

It was also used in economics for modelling consumption and investment, [5] to approximate current-voltage characteristics of field-effect transistors and light-emitting diodes, [6] to design antenna feeders, [7] and analyze plasma temperatures and densities in the divertor region of fusion reactors. [8]

Sensitivity to parameters

Derivative of the function is defined by the formula:

The following conditions are keeping the function limited on y-axes: ac, bd.

A family of recurrence-generated parametric Soboleva modified hyperbolic tangent activation functions (NPSMHTAF, FPSMHTAF) was studied with parameters a = c and b = d. [9] It is worth noting that in this case, the function is not sensitive to flipping the left and right-sides parameters:

EquationLeft prevalenceRight prevalence
SMHTAF 03a.png
SMHTAF 03b.png

The function is sensitive to ratio of the denominator coefficients and often is used without coefficients in the numerator:

EquationBasic chartScaled function

Extremum estimates:

SMHTAF 04a.png
SMHTAF 04b.png

With parameters a = b = c = d = 1 the modified hyperbolic tangent function reduces to the conventional tanh(x) function, whereas for a = b = 1 and c = d = 0, the term becomes equal to sinh(x).

See also

Notes

  1. 1 2 Soboleva proposed the name "modified hyperbolic tangent" (mtanh, mth), but since other authors used this name also for other functions, some authors have started to refer to this function as "Soboleva modified hyperbolic tangent".

Related Research Articles

<span class="mw-page-title-main">Angle</span> Figure formed by two rays meeting at a common point

In Euclidean geometry, an angle is the figure formed by two rays, called the sides of the angle, sharing a common endpoint, called the vertex of the angle. Angles formed by two rays are also known as plane angles as they lie in the plane that contains the rays. Angles are also formed by the intersection of two planes; these are called dihedral angles. Two intersecting curves may also define an angle, which is the angle of the rays lying tangent to the respective curves at their point of intersection.

<span class="mw-page-title-main">Hyperbola</span> Plane curve: conic section

In mathematics, a hyperbola is a type of smooth curve lying in a plane, defined by its geometric properties or by equations for which it is the solution set. A hyperbola has two pieces, called connected components or branches, that are mirror images of each other and resemble two infinite bows. The hyperbola is one of the three kinds of conic section, formed by the intersection of a plane and a double cone. If the plane intersects both halves of the double cone but does not pass through the apex of the cones, then the conic is a hyperbola.

<span class="mw-page-title-main">Trigonometric functions</span> Functions of an angle

In mathematics, the trigonometric functions are real functions which relate an angle of a right-angled triangle to ratios of two side lengths. They are widely used in all sciences that are related to geometry, such as navigation, solid mechanics, celestial mechanics, geodesy, and many others. They are among the simplest periodic functions, and as such are also widely used for studying periodic phenomena through Fourier analysis.

<span class="mw-page-title-main">Hyperbolic functions</span> Collective name of 6 mathematical functions

In mathematics, hyperbolic functions are analogues of the ordinary trigonometric functions, but defined using the hyperbola rather than the circle. Just as the points (cos t, sin t) form a circle with a unit radius, the points (cosh t, sinh t) form the right half of the unit hyperbola. Also, similarly to how the derivatives of sin(t) and cos(t) are cos(t) and –sin(t) respectively, the derivatives of sinh(t) and cosh(t) are cosh(t) and +sinh(t) respectively.

<span class="mw-page-title-main">Logistic function</span> S-shaped curve

A logistic function or logistic curve is a common S-shaped curve with the equation

<span class="mw-page-title-main">Sigmoid function</span> Mathematical function having a characteristic S-shaped curve or sigmoid curve

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

<span class="mw-page-title-main">Cubic equation</span> Polynomial equation of degree 3

In algebra, a cubic equation in one variable is an equation of the form

<span class="mw-page-title-main">Hyperbolic geometry</span> Non-Euclidean geometry

In mathematics, hyperbolic geometry is a non-Euclidean geometry. The parallel postulate of Euclidean geometry is replaced with:

An artificial neuron is a mathematical function conceived as a model of biological neurons in a neural network. Artificial neurons are the elementary units of artificial neural networks. The artificial neuron receives one or more inputs and sums them to produce an output. Usually, each input is separately weighted, and the sum is often added to a term known as a bias, before being passed through a non-linear function known as an activation function or transfer function. The transfer functions usually have a sigmoid shape, but they may also take the form of other non-linear functions, piecewise linear functions, or step functions. They are also often monotonically increasing, continuous, differentiable and bounded. Non-monotonic, unbounded and oscillating activation functions with multiple zeros that outperform sigmoidal and ReLU-like activation functions on many tasks have also been recently explored. The thresholding function has inspired building logic gates referred to as threshold logic; applicable to building logic circuits resembling brain processing. For example, new devices such as memristors have been extensively used to develop such logic in recent times.

<span class="mw-page-title-main">PFC Levski Sofia</span> Bulgarian football club

PFC Levski Sofia is a Bulgarian professional association football club based in Sofia, which competes in the First League, the top division of the Bulgarian football league system. The club was founded on 24 May 1914 by a group of high school students, and is named after Vasil Levski, a Bulgarian revolutionary renowned as the national hero of the country.

In mathematics, linearization is finding the linear approximation to a function at a given point. The linear approximation of a function is the first order Taylor expansion around the point of interest. In the study of dynamical systems, linearization is a method for assessing the local stability of an equilibrium point of a system of nonlinear differential equations or discrete dynamical systems. This method is used in fields such as engineering, physics, economics, and ecology.

<span class="mw-page-title-main">Hyperbolic secant distribution</span> Continuous probability distribution

In probability theory and statistics, the hyperbolic secant distribution is a continuous probability distribution whose probability density function and characteristic function are proportional to the hyperbolic secant function. The hyperbolic secant function is equivalent to the reciprocal hyperbolic cosine, and thus this distribution is also called the inverse-cosh distribution.

The International Mathematics Competition (IMC) for University Students is an annual mathematics competition open to all undergraduate students of mathematics. Participating students are expected to be at most twenty three years of age at the time of the IMC. The IMC is primarily a competition for individuals, although most participating universities select and send one or more teams of students. The working language is English.

<span class="mw-page-title-main">Inverse hyperbolic functions</span> Mathematical functions

In mathematics, the inverse hyperbolic functions are inverses of the hyperbolic functions, analogous to the inverse circular functions. There are six in common use: inverse hyperbolic sine, inverse hyperbolic cosine, inverse hyperbolic tangent, inverse hyperbolic cosecant, inverse hyperbolic secant, and inverse hyperbolic cotangent. They are commonly denoted by the symbols for the hyperbolic functions, prefixed with arc- or ar-.

In mathematics, the elasticity or point elasticity of a positive differentiable function f of a positive variable at point a is defined as

This is a summary of differentiation rules, that is, rules for computing the derivative of a function in calculus.

<span class="mw-page-title-main">Hilmi İbar</span> Chemist, Pedagogue

Hilmi İbar is professor of chemistry, former dean of the pedagogic faculty and former head of the International Office at the Trakya University in Edirne. He is also vice president of the Balkan Universities Network.

<span class="mw-page-title-main">Rectifier (neural networks)</span> Activation function

In the context of artificial neural networks, the rectifier or ReLU activation function is an activation function defined as the positive part of its argument:

Dink is a village in Southern Bulgaria, Maritsa Municipality, Plovdiv Province. As of 15 June 2020, the village has a population of 909.

References

  1. Soboleva, Elena Vladimirovna; Beskorovainyi, Vladimir Valentinovich (2008). The utility function in problems of structural optimization of distributed objectsФункция для оценки полезности альтернатив в задачах структурной оптимизации территориально распределенных объектов. Четверта наукова конференція Харківського університету Повітряних Сил імені Івана Кожедуба, 16–17 квітня 2008 (The fourth scientific conference of the Ivan Kozhedub Kharkiv University of Air Forces, 16–17 April 2008) (in Russian). Kharkiv, Ukraine: Kharkiv University of Air Force (HUPS/ХУПС). p. 121.
  2. Soboleva, Elena Vladimirovna (2009). S-образная функция полезности част-ных критериев для многофакторной оценки проектных решений[The S-shaped utility function of individual criteria for multi-objective decision-making in design]. Материалы XIII Международного молодежного форума «Радиоэлектро-ника и молодежь в XXI веке» (Materials of the 13th international youth forum "Radioelectronics and youth in the 21st century") (in Russian). Kharkiv, Ukraine: Kharkiv National University of Radioelectronics (KNURE/ХНУРЕ). p. 247.
  3. Beskorovainyi, Vladimir Valentinovich; Soboleva, Elena Vladimirovna (2010). ИДЕНТИФИКАЦИЯ ЧАСТНОй ПОлЕЗНОСТИ МНОГОФАКТОРНЫХ АлЬТЕРНАТИВ С ПОМОЩЬЮ S-ОБРАЗНЫХ ФУНКЦИй [Identification of utility functions in multi-objective choice modelling by using S-shaped functions](PDF). Problemy Bioniki: Respublikanskij Mežvedomstvennyj Naučno-Techničeskij SbornikБИОНИКА ИНТЕЛЛЕКТА[Bionics of Intelligence] (in Russian). Vol. 72, no. 1. Kharkiv National University of Radioelectronics (KNURE/ХНУРЕ). pp. 50–54. ISSN   0555-2656. UDK 519.688: 004.896. Archived (PDF) from the original on 2022-06-21. Retrieved 2020-06-19. (5 pages)
  4. Malinova, Anna; Golev, Angel; Iliev, Anton; Kyurkchiev, Nikolay (August 2017). "A Family Of Recurrence Generating Activation Functions Based On Gudermann Function" (PDF). International Journal of Engineering Researches and Management Studies. Faculty of Mathematics and Informatics, University of Plovdiv "Paisii Hilendarski", Plovdiv, Bulgaria. 4 (8): 38–48. ISSN   2394-7659. Archived (PDF) from the original on 2022-07-14. Retrieved 2020-06-19. (11 pages)
  5. Orlando, Giuseppe (2016-07-01). "A discrete mathematical model for chaotic dynamics in economics: Kaldor's model on business cycle". Mathematics and Computers in Simulation. 8th Workshop STRUCTURAL DYNAMICAL SYSTEMS: Computational Aspects; Edited by Nicoletta Del Buono, Roberto Garrappa and Giulia Spaletta and Nonstandard Applications of Computer Algebra (ACA’2013); Edited by Francisco Botana, Antonio Hernando, Eugenio Roanes-Lozano and Michael J. Wester. 125: 83–98. doi:10.1016/j.matcom.2016.01.001. ISSN   0378-4754.
  6. Tuev, Vasily I.; Uzhanin, Maxim V. (2009). ПРИМЕНЕНИЕ МОДИФИЦИРОВАННОЙ ФУНКЦИИ ГИПЕРБОЛИЧЕСКОГО ТАНГЕНСА ДЛЯ АППРОКСИМАЦИИ ВОЛЬТАМПЕРНЫХ ХАРАКТЕРИСТИК ПОЛЕВЫХ ТРАНЗИСТОРОВ [Using modified hyperbolic tangent function to approximate the current-voltage characteristics of field-effect transistors] (in Russian). Tomsk, Russia: Tomsk Politehnic University (TPU/ТПУ). pp. 135–138. No. 4/314. Archived from the original on 2017-08-15. Retrieved 2015-11-05. (4 pages)
  7. Golev, Angel; Djamiykov, Todor; Kyurkchiev, Nikolay (2017-11-23) [2017-10-09, 2017-08-19]. "Sigmoidal Functions In Antenna-Feeder Technique" (PDF). International Journal of Pure and Applied Mathematics. Faculty of Mathematics and Informatics, University of Plovdiv "Paisii Hilendarski", Plovdiv, Bulgaria / Technical University of Sofia, Sofia, Bulgaria: Academic Publications, Ltd. 116 (4): 1081–1092. doi:10.12732/ijpam.v116i4.23 (inactive 2024-01-31). ISSN   1311-8080. Archived (PDF) from the original on 2020-06-19. Retrieved 2020-06-19.{{cite journal}}: CS1 maint: DOI inactive as of January 2024 (link) (12 pages)
  8. Rubino, Giulio (2018-01-15) [2018-01-14]. Power Exhaust Data Analysis and Modeling Of Advanced Divertor Configuration (PDF) (Thesis). Joint Research Doctorate In Fusion Science And Engineering Cycle XXX (in English, Italian, and Portuguese). Padova, Italy: Centro Ricerche Fusione (CRF), Università degli Studi di Padova / Università degli Studi di Napoli Federico II / Instituto Superior Técnico (IST), Universidade de Lisboa. p. 84. ID 10811. Archived (PDF) from the original on 2020-06-19. Retrieved 2020-06-19. (2+viii+3*iii+102 pages)
  9. Golev, Angel; Iliev, Anton; Kyurkchiev, Nikolay (June 2017). "A Note on the Soboleva' Modified Hyperbolic Tangent Activation Function" (PDF). International Journal of Innovative Science, Engineering & Technology (JISET). Faculty of Mathematics and Informatics, University of Plovdiv "Paisii Hilendarski", Plovdiv, Bulgaria. 4 (6): 177–182. ISSN   2348-7968. Archived (PDF) from the original on 2020-06-19. Retrieved 2020-06-19. (6 pages)

Further reading