Seppo Linnainmaa
   HOME
*





Seppo Linnainmaa
Seppo Ilmari Linnainmaa (born 28 September 1945) is a Finnish mathematician and computer scientist. He was born in Pori. In 1974 he obtained the first doctorate ever awarded in computer science at the University of Helsinki. In 1976, he became Assistant Professor. From 1984 to 1985 he was Visiting Professor at the University of Maryland, USA. From 1986 to 1989 he was Chairman of the Finnish Artificial Intelligence Society. From 1989 to 2007, he was Research Professor at the VTT Technical Research Centre of Finland. He retired in 2007. Explicit, efficient error backpropagation in arbitrary, discrete, possibly sparsely connected, neural networks-like networks was first described in a 1970 master's thesis (Linnainmaa, 1970, 1976), albeit without reference to NNs,Jürgen Schmidhuber, (2015)Who Invented Backpropagation?/ref> when Linnainmaa introduced the reverse mode of automatic differentiation (AD), in order to efficiently compute the derivative of a differentiable composite function ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


picture info

Finns
Finns or Finnish people ( fi, suomalaiset, ) are a Baltic Finnic ethnic group native to Finland. Finns are traditionally divided into smaller regional groups that span several countries adjacent to Finland, both those who are native to these countries as well as those who have resettled. Some of these may be classified as separate ethnic groups, rather than subgroups of Finns. These include the Kvens and Forest Finns in Norway, the Tornedalians in Sweden, and the Ingrian Finns in Russia. Finnish, the language spoken by Finns, is closely related to other Balto-Finnic languages, e.g. Estonian and Karelian. The Finnic languages are a subgroup of the larger Uralic family of languages, which also includes Hungarian. These languages are markedly different from most other languages spoken in Europe, which belong to the Indo-European family of languages. Native Finns can also be divided according to dialect into subgroups sometimes called ''heimo'' (lit. ''tribe''), although suc ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


picture info

Composite Function
In mathematics, function composition is an operation that takes two function (mathematics), functions and , and produces a function such that . In this operation, the function is function application, applied to the result of applying the function to . That is, the functions and are composed to yield a function that maps in domain of a function, domain to in codomain . Intuitively, if is a function of , and is a function of , then is a function of . The resulting ''composite'' function is denoted , defined by for all in . The notation is read as " of ", " after ", " circle ", " round ", " about ", " composed with ", " following ", " then ", or " on ", or "the composition of and ". Intuitively, composing functions is a chaining process in which the output of function feeds the input of function . The composition of functions is a special case of the composition of relations, sometimes also denoted by \circ. As a result, all properties of composit ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


Finnish Computer Scientists
Finnish may refer to: * Something or someone from, or related to Finland * Culture of Finland * Finnish people or Finns, the primary ethnic group in Finland * Finnish language Finnish ( endonym: or ) is a Uralic language of the Finnic branch, spoken by the majority of the population in Finland and by ethnic Finns outside of Finland. Finnish is one of the two official languages of Finland (the other being Swedis ..., the national language of the Finnish people * Finnish cuisine See also * Finish (other) * Finland (other) * Suomi (other) * {{disambiguation Language and nationality disambiguation pages ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


Finnish Mathematicians
Finnish may refer to: * Something or someone from, or related to Finland * Culture of Finland * Finnish people or Finns, the primary ethnic group in Finland * Finnish language, the national language of the Finnish people * Finnish cuisine See also * Finish (other) * Finland (other) * Suomi (other) Suomi means ''Finland'' in Finnish. It may also refer to: *Finnish language * Suomi (surname) * Suomi, Minnesota, an unincorporated community * Suomi College, in Hancock, Michigan, now referred to as Finlandia University * Suomi Island, Western ... * {{disambiguation Language and nationality disambiguation pages ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


picture info

People From Pori
A person ( : people) is a being that has certain capacities or attributes such as reason, morality, consciousness or self-consciousness, and being a part of a culturally established form of social relations such as kinship, ownership of property, or legal responsibility. The defining features of personhood and, consequently, what makes a person count as a person, differ widely among cultures and contexts. In addition to the question of personhood, of what makes a being count as a person to begin with, there are further questions about personal identity and self: both about what makes any particular person that particular person instead of another, and about what makes a person at one time the same person as they were or will be at another time despite any intervening changes. The plural form "people" is often used to refer to an entire nation or ethnic group (as in "a people"), and this was the original meaning of the word; it subsequently acquired its use as a plural form of per ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


picture info

1945 Births
1945 marked the end of World War II and the fall of Nazi Germany and the Empire of Japan. It is also the only year in which Nuclear weapon, nuclear weapons Atomic bombings of Hiroshima and Nagasaki, have been used in combat. Events Below, the events of World War II have the "WWII" prefix. January * January 1 – WWII: ** Nazi Germany, Germany begins Operation Bodenplatte, an attempt by the ''Luftwaffe'' to cripple Allies of World War II, Allied air forces in the Low Countries. ** Chenogne massacre: German prisoners are allegedly killed by American forces near the village of Chenogne, Belgium. * January 6 – WWII: A German offensive recaptures Esztergom, Kingdom of Hungary (1920–1946), Hungary from the Russians. * January 12 – WWII: The Soviet Union begins the Vistula–Oder Offensive in Eastern Europe, against the German Army (Wehrmacht), German Army. * January 13 – WWII: The Soviet Union begins the East Prussian Offensive, to eliminate German forces in East Pruss ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


Living People
Related categories * :Year of birth missing (living people) / :Year of birth unknown * :Date of birth missing (living people) / :Date of birth unknown * :Place of birth missing (living people) / :Place of birth unknown * :Year of death missing / :Year of death unknown * :Date of death missing / :Date of death unknown * :Place of death missing / :Place of death unknown * :Missing middle or first names See also * :Dead people * :Template:L, which generates this category or death years, and birth year and sort keys. : {{DEFAULTSORT:Living people 21st-century people People by status ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


picture info

Machine Learning
Machine learning (ML) is a field of inquiry devoted to understanding and building methods that 'learn', that is, methods that leverage data to improve performance on some set of tasks. It is seen as a part of artificial intelligence. Machine learning algorithms build a model based on sample data, known as training data, in order to make predictions or decisions without being explicitly programmed to do so. Machine learning algorithms are used in a wide variety of applications, such as in medicine, email filtering, speech recognition, agriculture, and computer vision, where it is difficult or unfeasible to develop conventional algorithms to perform the needed tasks.Hu, J.; Niu, H.; Carrasco, J.; Lennox, B.; Arvin, F.,Voronoi-Based Multi-Robot Autonomous Exploration in Unknown Environments via Deep Reinforcement Learning IEEE Transactions on Vehicular Technology, 2020. A subset of machine learning is closely related to computational statistics, which focuses on making predicti ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  




Multi-layer Perceptrons
A multilayer perceptron (MLP) is a fully connected class of feedforward artificial neural network (ANN). The term MLP is used ambiguously, sometimes loosely to mean ''any'' feedforward ANN, sometimes strictly to refer to networks composed of multiple layers of perceptrons (with threshold activation); see . Multilayer perceptrons are sometimes colloquially referred to as "vanilla" neural networks, especially when they have a single hidden layer. An MLP consists of at least three layers of nodes: an input layer, a hidden layer and an output layer. Except for the input nodes, each node is a neuron that uses a nonlinear activation function. MLP utilizes a supervised learning technique called backpropagation for training. Its multiple layers and non-linear activation distinguish MLP from a linear perceptron. It can distinguish data that is not linearly separable.Cybenko, G. 1989. Approximation by superpositions of a sigmoidal function '' Mathematics of Control, Signals, and Systems'' ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


Chain Rule
In calculus, the chain rule is a formula that expresses the derivative of the composition of two differentiable functions and in terms of the derivatives of and . More precisely, if h=f\circ g is the function such that h(x)=f(g(x)) for every , then the chain rule is, in Lagrange's notation, :h'(x) = f'(g(x)) g'(x). or, equivalently, :h'=(f\circ g)'=(f'\circ g)\cdot g'. The chain rule may also be expressed in Leibniz's notation. If a variable depends on the variable , which itself depends on the variable (that is, and are dependent variables), then depends on as well, via the intermediate variable . In this case, the chain rule is expressed as :\frac = \frac \cdot \frac, and : \left.\frac\_ = \left.\frac\_ \cdot \left. \frac\_ , for indicating at which points the derivatives have to be evaluated. In integration, the counterpart to the chain rule is the substitution rule. Intuitive explanation Intuitively, the chain rule states that knowing the instantaneous rate of cha ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


picture info

Graph Of A Function
In mathematics, the graph of a function f is the set of ordered pairs (x, y), where f(x) = y. In the common case where x and f(x) are real numbers, these pairs are Cartesian coordinates of points in two-dimensional space and thus form a subset of this plane. In the case of functions of two variables, that is functions whose domain consists of pairs (x, y), the graph usually refers to the set of ordered triples (x, y, z) where f(x,y) = z, instead of the pairs ((x, y), z) as in the definition above. This set is a subset of three-dimensional space; for a continuous real-valued function of two real variables, it is a surface. In science, engineering, technology, finance, and other areas, graphs are tools used for many purposes. In the simplest case one variable is plotted as a function of another, typically using rectangular axes; see '' Plot (graphics)'' for details. A graph of a function is a special case of a relation. In the modern foundations of mathematics, and, typicall ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


picture info

Differentiable Function
In mathematics, a differentiable function of one real variable is a function whose derivative exists at each point in its domain. In other words, the graph of a differentiable function has a non-vertical tangent line at each interior point in its domain. A differentiable function is smooth (the function is locally well approximated as a linear function at each interior point) and does not contain any break, angle, or cusp. If is an interior point in the domain of a function , then is said to be ''differentiable at'' if the derivative f'(x_0) exists. In other words, the graph of has a non-vertical tangent line at the point . is said to be differentiable on if it is differentiable at every point of . is said to be ''continuously differentiable'' if its derivative is also a continuous function over the domain of the function f. Generally speaking, is said to be of class if its first k derivatives f^(x), f^(x), \ldots, f^(x) exist and are continuous over the domain of the func ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]