Commune · Savoirs
programmation différentiable
Programming paradigm in which a numeric computer program can be differentiated throughout via automatic differentiation, allowing for machine learning based on gradient descent etc.
Differentiable programming is a programming paradigm in which a numeric computer program can be differentiated throughout via automatic differentiation. This allows for gradient-based optimization of parameters in the program, often via gradient descent, as well as other learning approaches that are based on higher-order derivative information.
Sur Wikipédia
Texte en anglais Pas encore d'article dans ta langue : extrait en anglais.
Differentiable programming is a programming paradigm in which a numeric computer program can be differentiated throughout via automatic differentiation. This allows for gradient-based optimization of parameters in the program, often via gradient descent, as well as other learning approaches that are based on higher-order derivative information. Differentiable programming has found use in a wide variety of areas, particularly scientific computing and machine learning. One of the early proposals to adopt such a framework in a systematic fashion to improve upon learning algorithms was made by the Advanced Concepts Team at the European Space Agency in early 2016.
Texte : Wikipédia en anglais, CC BY-SA 4.0. ·
Cartes voisines
-
N★★
Neural field
A neural field is a type of neural network that models a mathematical field in a continuous and differentiable way
-
★★★
Programmation dynamique
Méthode algorithmique de résolution de problèmes d'optimisation
-
★
Algorithme à évolution différentielle
-
D★
Dataflow programming
Programming paradigm that models program as a directed graph of data flow between operations
-
a★
atelier de génie logiciel
Type of computer programming where some mechanism generates a computer program allowing programmers to write code at higher abstraction levels
-
★★★★
Calcul différentiel
Branche des mathématiques