Skip to main content

Semi-supervised Learning

Ways of Doing Semi-supervised algorithm
  1. Transductive SVM ( minimize the risk directly )
  2. Co-training and Tri-training ( using two/three different view of the same datasets)
  3. Genetic Algorithm
  4. Non-parametric approach ( modified KDE convergence algorithm )
  5. Parametric approach ( modified EM algorithm )
  6. Graph-based approach
Labels:

Comments

Post a Comment

Popular posts from this blog

Web App Scaling with Flask Blueprint and Namespaces

A real-world Flask-RESTX-based API  may have multiple namespaces. The best practice for scaling a web application is to use a blueprint along with multiple namespace. The namespace is used to group a set of CRUD operations for a specific resource.  Blueprint can be used to combine (mixing) multiple namespaces. Here’s an example directory structure: project\ ├── app.py # Application file ├── apis #    ├── v20 # API directory    │   ├── __init__.py    │   ├── specs.py # API namespaces and REST methods    │   ├── steps.py # API namespaces and REST methods    └── v20bp.py # API blueprint file Here is an example app.py. Using a blue print allow you to mount your API on any url prefix. from flask import Flask from apis.v20bp import blueprint as api app = ...
Post a Comment
Read more