Skip to content

Machine Learning Side Projects I worked on during my free time. It's more for dataset exploring and algorithms experimenting rather than problem-solving.

Notifications You must be signed in to change notification settings

wayofnumbers/SideProjects

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Michael Li - Side Machine Learning Projects

About

These are some of my side projects I did when learning Machine Learning and to explore variant machine learning algorithms and models. It's more for dataset exploring and algorithms experimenting rather than problem solving.

Datasets are all public available.

Table of Contents

Image Recognition

PCA, Feature Extraction, and Kernels

Notebook

The algorithms used in this project is rather old, these are the techniques before the debut of CNN, yet the data preprocessing, feature engineering, etc. can still provide some reference.

Techniques used:

  • PCA
  • Image Pre-Processing
  • Image Visualization
  • Edge Detection
  • Daisy Feature Extraction
  • Gabor Filter

Covolutional Neural Network (CNN)

Notebook

Same image recognition task and dataset with the PCA project, yet building MLN(Multi-Layer Neural Network) and variuos CNN models from scratch using keras.

Models built and compared:

  • Multi-Layer Neural Network
  • Simple CNN with relu activation and Maxpooling
  • CNN with dropout
  • LeNet
  • Basic ResNet
  • RasNet50

FashionMNIST w/ PyTorch from scratch

Notebook

Article

Exploring PyTorch, built a simple multi-layer CNN for the FashionMNIST dataset.

Machine Learning

Logistic Regression

Notebook

  • Using various Logistic Regression and optimization algorithms to prodict Cellphone Sales Prices.
  • Compares the models with scikitlearn's model interms of accuracy and training time.

Feature Engineering, Cross Validation, Multi-Layer Neural Network

Notebook

Used PCA to do feature reduction, train/validation/test split, Multi-Layer Neural Network from scratch.

Natrual Language Processing

Texa Data Manipulation and Visualisations

Notebook

Techniques Used:

  • Stemming
  • Stop Words
  • Bag-of-word Representation
  • Tf-Idf Representation
  • Word Frequency
  • Word Cloud Generation
  • Masked Word Clouds

About

Machine Learning Side Projects I worked on during my free time. It's more for dataset exploring and algorithms experimenting rather than problem-solving.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published