Common · Knowledge
Differentiable programming
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.
From Wikipedia
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.
Text: Wikipédia, CC BY-SA 4.0. ·
Related cards
-
N★★
Neural field
A neural field is a type of neural network that models a mathematical field in a continuous and differentiable way
-
★★★
Dynamic programming
Problem optimization method that simplifies a complicated problem by decomposing it into simpler subproblems recursively
-
★
Differential evolution
Method of mathematical optimization
-
D★
Dataflow programming
Programming paradigm that models program as a directed graph of data flow between operations
-
A★
Automatic programming
Type of computer programming where some mechanism generates a computer program allowing programmers to write code at higher abstraction levels
-
★★★★
Differential calculus
Subfield of calculus