neural-networks-basics

This repository aims at providing simple illustration to the main concepts of neural networks.

mainly it consists of two parts, theoretical and practical parts. the theoretical part covers the main concepts of neural networks such as propagation, gradient descent, derivation and many other concepts, while the practical part gives you a hands-on experience on coding neural networks just using numpy libarary.

the original material of this repository is taken from Andrew Ng course of neural networks on coursera.

The main topics covered up to the moment are:

Neural Networks and Deep Learning

1. Logistic Regression as a Neural Network [Completed].
2. Shallow Neural Network [Completed].
3. Deep Neural Network [Completed].

Improving Deep Neural Network: Hyperparameters Tuning, Regularization and Optimization.

1. Practical Aspects of Deep Learning [Completed].
2. Optimization Algorithms [Completed].
3. Hyperparameter tuning, Batch Normalization and Programming Frameworks [Under Progress]