-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
6 changed files
with
178 additions
and
78 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1 +1,9 @@ | ||
# AdaptiveFlows.jl | ||
|
||
AdaptiveFlows.jl provides a framework for working with Normalizing Flows, a method from machine learning that transforms complex probability distributions into simpler ones, often a $D$-dimensional standard Normal distribution. This transformation is achieved through a series of invertible and differentiable mappings. | ||
|
||
The package is particularly useful when dealing with real-world data that follow challenging probability distributions, making traditional statistical methods difficult or impossible to apply. By shifting the focus from the complex distribution itself to finding a transformation from it to a simple distribution, Normalizing Flows can alleviate these difficulties. | ||
|
||
This package offers functionality for both forward and inverse transformations. This means that not only can it transform samples drawn from a complex distribution so that the transformed samples follow a simple distribution, but it can also transform samples drawn from a simple distribution so that the transformed samples follow a complex target distribution. | ||
|
||
With these functionalities, AdaptiveFlows.jl provides tools for density evaluation and sampling of a target distribution, making it a versatile tool for tasks such as clustering and classification, density estimation, and variational inference. |
Oops, something went wrong.