Neural-Networks-Intro

Harvard's CS109A course was used as reference to model Neural Networks from scratch (https://harvard-iacs.github.io/2020-CS109A/)

Simple and multi linear Perceptron (MLP)
MLP from first principles on Iris dataset
MLP using Keras
Review of Keras
Use Keras on Fashion MNSIT dataset
Gradient Descent methods and plots
Back propagation from first principles
Regularization methods to improve neural networks - L1 and L2 norm penalties, early stopping, data augmentation, and dropout.

Name		Name	Last commit message	Last commit date
Latest commit History 12 Commits
data		data
images		images
notes		notes
1.1 - Perceptron and MLP.ipynb		1.1 - Perceptron and MLP.ipynb
1.2 - MLP by hand on Iris.ipynb		1.2 - MLP by hand on Iris.ipynb
1.3 - MLP using Keras.ipynb		1.3 - MLP using Keras.ipynb
1.4 - Keras for ANN.ipynb		1.4 - Keras for ANN.ipynb
1.5 - Tensors - Fashion eg.ipynb		1.5 - Tensors - Fashion eg.ipynb
2.1 - Gradient Descent.ipynb		2.1 - Gradient Descent.ipynb
2.2 - Gradient Descent - more methods.ipynb		2.2 - Gradient Descent - more methods.ipynb
2.3 - Back-propogation - chain rule.ipynb		2.3 - Back-propogation - chain rule.ipynb
3.1 - Regularization methods.ipynb		3.1 - Regularization methods.ipynb
Neural Networks - book.ipynb		Neural Networks - book.ipynb
README.md		README.md
fashion_model.h5		fashion_model.h5

Provide feedback