Metadata-Version: 1.2
Name: selfsne
Version: 0.0.1
Summary: Self-Supervised Noise Embeddings (Self-SNE) for dimensionality reduction and clustering
Home-page: https://github.com/jgraving/selfsne
Author: Jacob Graving <jgraving@gmail.com>
Author-email: jgraving@gmail.com
Maintainer: Jacob Graving <jgraving@gmail.com>
Maintainer-email: jgraving@gmail.com
License: Apache 2.0
Download-URL: https://github.com/jgraving/selfsne.git
Description: Self-SNE is a probabilistic self-supervised deep learning model for compressing high-dimensional data to a low-dimensional embedding. It is a general-purpose algorithm that works with multiple types of data including images, sequences, and tabular data. It uses self-supervised objectives, such as InfoNCE, to preserve structure in the compressed latent space. Self-SNE can also (optionally) simultaneously learn a cluster distribution (a prior over the latent embedding) during optimization. Overlapping clusters are automatically combined by optimizing a variational upper bound on entropy, so the number of clusters does not have to be specified manually — provided the number of initial clusters is large enough. Self-SNE produces embeddings with similar quality to existing dimensionality reduction methods; can detect outliers; scales to large, out-of-core datasets; and can easily add new data to an existing embedding/clustering.
        
        
Platform: UNKNOWN
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: Unix
Classifier: Operating System :: MacOS
