Skip to content

A project that shows my progress from implementing a single neuron to full-fledged neural networks FROM SCRATCH..

Notifications You must be signed in to change notification settings

rviole/machine-learning-from-scratch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

39 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Machine Learning Projects From Scratch

A set of Machine Learning Projects developer from scratch. Serves as a Portfolio project.

🚧 In progress ...

Repository Structure

Project 📘Description 🔑 Key Change Link
Stable 1.0 Linear Regression model built from scratch:
  • Input Features: 1
  • Output Features: 1
  • Loss: MSE (Mean Squared Error)
  • Optimizer: None (manual gradient descent)
  • Activation: Linear
None Link
Stable 1.1 Linear Regression model built from scratch:
  • Input Features: 1
  • Output Features: 1
  • Loss: MSE (Mean Squared Error)
  • Optimizer: Custom with Learning Rate Scheduler
  • Activation: Linear
  • A Custom Optimizer with a Learning Rate Scheduler.
  • An automatic Weight Update
Link
Stable 1.2 Linear Regression model built from scratch:
  • Input Features: 2
  • Output Features: 1
  • Loss: MSE (Mean Squared Error)
  • Optimizer: Custom Momuntum-based
  • Activation: Linear
  • Momentum Based Optimizer
  • Multi Input: 2
Link
Stable 2.0 Linear Regression model built from scratch:
  • Layers: 2
  • Input Features: 2
  • Output Features: 1
  • Loss: MSE (Mean Squared Error)
  • Optimizer: Adam
  • Activation: ReLU
  • Adam Optimizer
  • ReLU Activation
  • Multi-Layer Network
  • Non-linear Problem
Link

About

A project that shows my progress from implementing a single neuron to full-fledged neural networks FROM SCRATCH..

Resources

Stars

Watchers

Forks