Discover enricivi/SEMI-FALKON Open Source project

Stars
4
Rank 3,304,323 (Top 66 %)
Language
Python
License
MIT License
Created over 6 years ago
Updated about 4 years ago

enricivi

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Falkon is one of the most efficient algorithm able to work in a supervised large scale setting. This method is the result of a combination of three simple principles: sub-sampling, preconditioning and iterative solvers. In order to extend FALKON usability we have designed an extension able to work in a semi-supervised scenario.

growing_hierarchical_som

Self-Organizing Map [https://en.wikipedia.org/wiki/Self-organizing_map] is a popular method to perform cluster analysis. SOM shows two main limitations: fixed map size constraints how the data is being mapped and hierarchical relationships are not easily recognizable. Thus Growing Hierarchical SOM has been designed to overcome this issues

Python

adversarial_training_methods

Implementation of the methods proposed in **Adversarial Training Methods for Semi-Supervised Text Classification** on IMDB dataset (without pre-training)

Jupyter Notebook

super_resolution

Super-resolution is a technique that constructs an high-resolution image from several observed low-resolution images.

MATLAB

image_viewer

A simple image viewer capable of showing EXIF tags

Python