Python for Deep Learning: Build Neural Networks in Python

Course Curriculum

Chapter 1: Introduction to Deep Learning

Lecture 1: What is a Deep Learning ?

Lecture 2: Course Materials

Lecture 3: Why is Deep Learning Important?

Lecture 4: Software and Frameworks

Chapter 2: Artificial Neural Networks (ANN)

Lecture 1: Introduction

Lecture 2: Anatomy and function of neurons

Lecture 3: An introduction to the neural network

Lecture 4: Architecture of a neural network

Chapter 3: Propagation of information in ANNs

Lecture 1: Feed-forward and Back Propagation Networks

Lecture 2: Backpropagation In Neural Networks

Lecture 3: Minimizing the cost function using backpropagation

Chapter 4: Neural Network Architectures

Lecture 1: Single layer perceptron (SLP) model

Lecture 2: Radial Basis Network (RBN)

Lecture 3: Multi-layer perceptron (MLP) Neural Network

Lecture 4: Recurrent neural network (RNN)

Lecture 5: Long Short-Term Memory (LSTM) networks

Lecture 6: Hopfield neural network

Lecture 7: Boltzmann Machine Neural Network

Chapter 5: Activation Functions

Lecture 1: What is the Activation Function?

Lecture 2: Important Terminologies

Lecture 3: The sigmoid function

Lecture 4: Hyperbolic tangent function

Lecture 5: Softmax function

Lecture 6: Rectified Linear Unit (ReLU) function

Lecture 7: Leaky Rectified Linear Unit function

Chapter 6: Gradient Descent Algorithm

Lecture 1: What is Gradient Decent?

Lecture 2: What is Stochastic Gradient Decent?

Lecture 3: Gradient Decent vs Stochastic Gradient Decent

Chapter 7: Summary Overview of Neural Networks

Lecture 1: How artificial neural networks work?

Lecture 2: Advantages of Neural Networks

Lecture 3: Disadvantages of Neural Networks

Lecture 4: Applications of Neural Networks

Chapter 8: Implementation of ANN in Python

Lecture 1: Introduction

Lecture 2: Exploring the dataset

Lecture 3: Problem Statement

Lecture 4: Data Pre-processing

Lecture 5: Loading the dataset

Lecture 6: Splitting the dataset into independent and dependent variables

Lecture 7: Label encoding using scikit-learn

Lecture 8: One-hot encoding using scikit-learn

Lecture 9: Training and Test Sets: Splitting Data

Lecture 10: Feature scaling

Lecture 11: Building the Artificial Neural Network

Lecture 12: Adding the input layer and the first hidden layer

Lecture 13: Adding the next hidden layer

Lecture 14: Adding the output layer

Lecture 15: Compiling the artificial neural network

Lecture 16: Fitting the ANN model to the training set

Lecture 17: Predicting the test set results

Chapter 9: Convolutional Neural Networks (CNN)

Lecture 1: Introduction

Lecture 2: Components of convolutional neural networks

Lecture 3: Convolution Layer

Lecture 4: Pooling Layer

Lecture 5: Fully connected Layer

Chapter 10: Implementation of CNN in Python

Lecture 1: Dataset

Lecture 2: Importing libraries

Lecture 3: Building the CNN model

Lecture 4: Accuracy of the model

Chapter 11: BONUS Section – Don't Miss Out

Lecture 1: BONUS Section – Don't Miss Out