Skip to content

🌳 Probabilistic and deep learning examples, including a neural net to classify hand drawn tree diagrams, and a CGAN to generate them.

Notifications You must be signed in to change notification settings

LucyIvatt/probabilistic-and-deep-learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

66 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

probabilistic-and-deep-learning

Python Jupyter Notebook NumPy scikit-learn Pandas Matplotlib PyTorch

This repository contains various examples of probabilisic and deap learning within the notebook int3.ipynb.

Regression and classification

Example of least squares linear regression model predicting the value of a variable from three others. Also includes examples of data normalising, scaling, regularisation and their effects on the outcome.

Principal Component Analysis

Performs an example of principal component analysis

Hand drawn tree symbol classification

Creates a classification model for hand-drawn trees from an unbalanced dataset - used Weighted Random Sampling to prevent bias.

3363 / 3366 predictions correct with 99.91% accuracy

image image

Generating tree symbol images of a specific class

CGAN to generate the hand-drawn tree diagrams. Unfortunately suffered from mode collapse.

4 random images of each tree class:

image

Interpolation between 2 of each class:

image

All code submitted for masters module at the University of York - Intelligent Systems 3: Probabilistic and deep learning.

About

🌳 Probabilistic and deep learning examples, including a neural net to classify hand drawn tree diagrams, and a CGAN to generate them.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published