Logo
Unionpedia
Communication
Get it on Google Play
New! Download Unionpedia on your Android™ device!
Download
Faster access than browser!
 

Softmax function

Index Softmax function

In mathematics, the softmax function, or normalized exponential function, is a generalization of the logistic function that "squashes" a -dimensional vector \mathbf of arbitrary real values to a -dimensional vector \sigma(\mathbf) of real values, where each entry is in the range (0, 1, and all the entries add up to 1. The function is given by In probability theory, the output of the softmax function can be used to represent a categorical distribution – that is, a probability distribution over different possible outcomes. In fact, it is the gradient-log-normalizer of the categorical probability distribution. The softmax function is also the gradient of the LogSumExp function. The softmax function is used in various multiclass classification methods, such as multinomial logistic regression (also known as softmax regression), multiclass linear discriminant analysis, naive Bayes classifiers, and artificial neural networks. Specifically, in multinomial logistic regression and linear discriminant analysis, the input to the function is the result of distinct linear functions, and the predicted probability for the 'th class given a sample vector and a weighting vector is: This can be seen as the composition of linear functions \mathbf \mapsto \mathbf^\mathsf\mathbf_1, \ldots, \mathbf \mapsto \mathbf^\mathsf\mathbf_K and the softmax function (where \mathbf^\mathsf\mathbf denotes the inner product of \mathbf and \mathbf). The operation is equivalent to applying a linear operator defined by \mathbf to vectors \mathbf, thus transforming the original, probably highly-dimensional, input to vectors in a -dimensional space \mathbb^K. [1]

28 relations: Artificial neural network, Boltzmann distribution, Categorical distribution, Cross entropy, Differentiable function, Dirichlet distribution, Function composition, Hyperbolic function, Julia (programming language), Kronecker delta, Linear discriminant analysis, Linear function, Linearization, Logistic function, LogSumExp, Mathematics, Monotonic function, Multiclass classification, Multinomial logistic regression, Naive Bayes classifier, Probability distribution, Probability theory, Rectifier (neural networks), Reinforcement learning, Sigmoid function, Smooth maximum, Smoothness, Statistical mechanics.

Artificial neural network

Artificial neural networks (ANNs) or connectionist systems are computing systems vaguely inspired by the biological neural networks that constitute animal brains.

New!!: Softmax function and Artificial neural network · See more »

Boltzmann distribution

In statistical mechanics and mathematics, a Boltzmann distribution (also called Gibbs distribution Translated by J.B. Sykes and M.J. Kearsley. See section 28) is a probability distribution, probability measure, or frequency distribution of particles in a system over various possible states.

New!!: Softmax function and Boltzmann distribution · See more »

Categorical distribution

In probability theory and statistics, a categorical distribution (also called a generalized Bernoulli distribution, multinoulli distribution) is a discrete probability distribution that describes the possible results of a random variable that can take on one of K possible categories, with the probability of each category separately specified.

New!!: Softmax function and Categorical distribution · See more »

Cross entropy

In information theory, the cross entropy between two probability distributions p and q over the same underlying set of events measures the average number of bits needed to identify an event drawn from the set, if a coding scheme is used that is optimized for an "unnatural" probability distribution q, rather than the "true" distribution p. The cross entropy for the distributions p and q over a given set is defined as follows: where H(p) is the entropy of p, and D_(p \| q) is the Kullback–Leibler divergence of q from p (also known as the relative entropy of p with respect to q — note the reversal of emphasis).

New!!: Softmax function and Cross entropy · See more »

Differentiable function

In calculus (a branch of mathematics), a differentiable function of one real variable is a function whose derivative exists at each point in its domain.

New!!: Softmax function and Differentiable function · See more »

Dirichlet distribution

In probability and statistics, the Dirichlet distribution (after Peter Gustav Lejeune Dirichlet), often denoted \operatorname(\boldsymbol\alpha), is a family of continuous multivariate probability distributions parameterized by a vector \boldsymbol\alpha of positive reals.

New!!: Softmax function and Dirichlet distribution · See more »

Function composition

In mathematics, function composition is the pointwise application of one function to the result of another to produce a third function.

New!!: Softmax function and Function composition · See more »

Hyperbolic function

In mathematics, hyperbolic functions are analogs of the ordinary trigonometric, or circular, functions.

New!!: Softmax function and Hyperbolic function · See more »

Julia (programming language)

Julia is a high-level dynamic programming language designed to address the needs of high-performance numerical analysis and computational science, without the typical need of separate compilation to be fast, while also being effective for general-purpose programming, web use or as a specification language.

New!!: Softmax function and Julia (programming language) · See more »

Kronecker delta

In mathematics, the Kronecker delta (named after Leopold Kronecker) is a function of two variables, usually just non-negative integers.

New!!: Softmax function and Kronecker delta · See more »

Linear discriminant analysis

Linear discriminant analysis (LDA), normal discriminant analysis (NDA), or discriminant function analysis is a generalization of Fisher's linear discriminant, a method used in statistics, pattern recognition and machine learning to find a linear combination of features that characterizes or separates two or more classes of objects or events.

New!!: Softmax function and Linear discriminant analysis · See more »

Linear function

In mathematics, the term linear function refers to two distinct but related notions.

New!!: Softmax function and Linear function · See more »

Linearization

In mathematics, linearization is finding the linear approximation to a function at a given point.

New!!: Softmax function and Linearization · See more »

Logistic function

A logistic function or logistic curve is a common "S" shape (sigmoid curve), with equation: where.

New!!: Softmax function and Logistic function · See more »

LogSumExp

The LogSumExp (LSE) function is a smooth approximation to the maximum function, mainly used by machine learning algorithms.

New!!: Softmax function and LogSumExp · See more »

Mathematics

Mathematics (from Greek μάθημα máthēma, "knowledge, study, learning") is the study of such topics as quantity, structure, space, and change.

New!!: Softmax function and Mathematics · See more »

Monotonic function

In mathematics, a monotonic function (or monotone function) is a function between ordered sets that preserves or reverses the given order.

New!!: Softmax function and Monotonic function · See more »

Multiclass classification

Not to be confused with multi-label classification. In machine learning, multiclass or multinomial classification is the problem of classifying instances into one of three or more classes.

New!!: Softmax function and Multiclass classification · See more »

Multinomial logistic regression

In statistics, multinomial logistic regression is a classification method that generalizes logistic regression to multiclass problems, i.e. with more than two possible discrete outcomes.

New!!: Softmax function and Multinomial logistic regression · See more »

Naive Bayes classifier

In machine learning, naive Bayes classifiers are a family of simple "probabilistic classifiers" based on applying Bayes' theorem with strong (naive) independence assumptions between the features.

New!!: Softmax function and Naive Bayes classifier · See more »

Probability distribution

In probability theory and statistics, a probability distribution is a mathematical function that provides the probabilities of occurrence of different possible outcomes in an experiment.

New!!: Softmax function and Probability distribution · See more »

Probability theory

Probability theory is the branch of mathematics concerned with probability.

New!!: Softmax function and Probability theory · See more »

Rectifier (neural networks)

In the context of artificial neural networks, the rectifier is an activation function defined as the positive part of its argument: f(x).

New!!: Softmax function and Rectifier (neural networks) · See more »

Reinforcement learning

Reinforcement learning (RL) is an area of machine learning inspired by behaviourist psychology, concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward.

New!!: Softmax function and Reinforcement learning · See more »

Sigmoid function

A sigmoid function is a mathematical function having a characteristic "S"-shaped curve or sigmoid curve.

New!!: Softmax function and Sigmoid function · See more »

Smooth maximum

In mathematics, a smooth maximum of an indexed family x1,..., xn of numbers is a differentiable approximation to the maximum function and the concept of smooth minimum is similarly defined.

New!!: Softmax function and Smooth maximum · See more »

Smoothness

In mathematical analysis, the smoothness of a function is a property measured by the number of derivatives it has that are continuous.

New!!: Softmax function and Smoothness · See more »

Statistical mechanics

Statistical mechanics is one of the pillars of modern physics.

New!!: Softmax function and Statistical mechanics · See more »

Redirects here:

Normalized exponential, Softmax activation function.

References

[1] https://en.wikipedia.org/wiki/Softmax_function

OutgoingIncoming
Hey! We are on Facebook now! »