Skip to content

Python based implementation of Convolution Neural Network using TensorFlow, Reinforcement Learning to train smart cab, Supervised Learning, and Unsupervised Learning techniques.

Notifications You must be signed in to change notification settings

pradeepsaiu/Machine-Learning-Algorithms-with-Python

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

31 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Machine Learning Examples

This Repository consists of different kinds of Machine Learnnig models, which are coded in Python.

Introduction to topics

  1. Supervised Learning:- In this kind of model, target label is used while training the model. E.g:- Predicting the housing prices of new houses, provided some sample about existing price of houses and some features which impact the housing price

    • Regression Techniques
    • Neural Networks
  2. Unsupervised Learning:- Here we have a un labeled data, meaning we want to classify data into various groups but we are not sure based on training data which class each data set belongs to.

    • Clustering:- Unsupervised learning can be done by seperating data into set of clusters or groups based on similarity score between different points. Similar data points can be clustered into similar groups.
  3. Reinforcement Learning:- In this kind of learning the model needn't be aware of how the system works, rather model learns when given +ve or -ve rewards based on it's action and stores the state information for future actions.

License

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. Please refer to Udacity Terms of Service for further information.w

About

Python based implementation of Convolution Neural Network using TensorFlow, Reinforcement Learning to train smart cab, Supervised Learning, and Unsupervised Learning techniques.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published