All Seasons

Season 1

• S01E01 Welcome

• S01E02 What is a neural network?

• S01E03 Supervised Learning with Neural Networks

• S01E04 About this Course

• S01E05 Course Resources

• S01E06 Geoffrey Hinton interview

Season 2

• S02E01 Binary Classification

• S02E02 Logistic Regression

• S02E03 Logistic Regression Cost Function

• S02E04 Gradient Descent

• S02E05 Derivatives

• S02E06 More Derivative Examples

• S02E07 Computation graph

• S02E08 Derivatives with a Computation Graph

• S02E09 Logistic Regression Gradient Descent

• S02E10 Gradient Descent on m Examples

• S02E11 Vectorization

• S02E12 More Vectorization Examples

• S02E13 Vectorizing Logistic Regression

• S02E14 Vectorizing Logistic Regression's Gradient Output

• S02E15 Broadcasting in Python

• S02E16 A note on python numpy vectors

• S02E17 Quick tour of Jupyter iPython Notebooks

• S02E18 Explanation of logistic regression cost function - optional

• S02E19 Pieter Abbeel interview

Season 3

• S03E01 Neural Networks Overview

• S03E02 Neural Network Representation

• S03E03 Computing a Neural Network's Output

• S03E04 Vectorizing across multiple examples

• S03E05 Explanation for Vectorized Implementation

• S03E06 Activation functions

• S03E07 Why do you need non-linear activation functions?

• S03E08 Derivatives of activation functions

• S03E09 Gradient descent for Neural Networks

• S03E10 Backpropagation intuition - optional

• S03E11 Random Initialization

• S03E12 Ian Goodfellow interview

Season 4

• S04E01 Deep L-layer neural network

• S04E02 Forward Propagation in a Deep Network

• S04E03 Getting your matrix dimensions right

• S04E04 Why deep representations?

• S04E05 Building blocks of deep neural networks

• S04E06 Forward and Backward Propagation

• S04E07 Parameters vs Hyperparameters

• S04E08 What does this have to do with the brain?