Shallow Neural Networks

#001A Introduction to Deep Learning

Deep learning is a sub-field of machine learning where artificial neural networks learn from large amounts of data

#001B Deep Learning, wait but why now?

Learn how to overcome performance plateau problem

#002A Binary classification

Everything you wanted to know about binary classification

#002B Image representation in a computer

How are images represented in a computer?

#003A Logistic Regression – Cost Function optimization

Why you really need to know what a Cost Function is?

#003B What is Gradient Descent?

Logistic Regression: Scratch vs. Scikit-Learn

How does Gradient Descent work?

#003C Gradient Descent in Python

How To Implement Gradient Descent In Python?

#004A Logistic Regression – The Computation Graph

Why do we need a Computation Graph?

#004B The Computation Graph – Example

Secrets about the Computation Graph - Example

#005A Logistic Regression from scratch with Gradient Descent

binary classification of two linearly separable datasets

How to implement Logistic Regression from scratch with Gradient Descent?

#005B Logistic Regression: Scratch vs. Scikit-Learn

Comparison of Logistic Regression from scratch and Logistic Regression from scikit – learn

#006A How to make Logistic Regression fast?

How to implement a vectorized Logistic Regression from scratch with Gradient Descent?

#006B Vectorization and Broadcasting in Python

The ultimate secret of vectorization

#007 Neural Networks - introduction

Representation of Neural Networks

#008 Shallow Neural Network

How to vectorize across multiple training examples?

#009 Activation functions and their derivatives

How to decide which activation function to use when building a Neural Network?

#010A Gradient Descent for Neural Networks

Computation graph for 2 – layer Neural Network

How to implement Gradient Descent for one hidden layer Neural Network?

#010 B How to train a shallow Neural Network with a Gradient Desecent?

How to build a shallow Neural Network in Python?

#010 C Random initialization of parameters in a Neural Network

Classification with a shallow Neural Network

Why do we need a random initialization?