{ C Language } Deep Learning From Ground Up™

Course Curriculum

Chapter 1: Introduction

Lecture 1: Introduction to Deep Learning

Chapter 2: Set Up

Lecture 1: Setting up an Integrated Development Environment (IDE)

Chapter 3: Introduction to Neural Networks

Lecture 1: The Single Input Single Output Neural Network

Lecture 2: Coding : Single Input Single Output Neural Network

Lecture 3: The Single Input Multiple Output Neural Network

Lecture 4: Coding : Single Input Multiple Output Neural Network

Lecture 5: The Multiple Input Single Output Neural Network

Lecture 6: Coding : Multiple Input Single Output Neural Network

Lecture 7: The Multiple Input Multiple Output Neural Network

Lecture 8: Coding : Multiple Input Multiple Output Neural Network

Lecture 9: The Hidden Layer Neural Network

Lecture 10: Coding : The Hidden Layer Neural Network

Lecture 11: Comparing and Finding Error

Lecture 12: Coding : Finding Error

Lecture 13: Understanding data representation in Machine Learning

Lecture 14: Understanding the "Learning" in Machine Learning

Lecture 15: Coding : Brute-force Learning

Lecture 16: Introduction to Gradient Descent

Lecture 17: Functional Description of a Biological Neuron

Chapter 4: Introduction to Neural Network (Part 2)

Lecture 1: Case Study : Building a Neural Network to Predict Muscle Gain

Lecture 2: Coding : Normalizing Datasets

Lecture 3: Coding : Random Initialization of Weights

Lecture 4: Understanding Activation Functions

Lecture 5: Coding : Forward Propagation

Lecture 6: Basics of Calculus

Chapter 5: Logistic Regression

Lecture 1: Case Study : Building a Neural Network to Detect Cats

Chapter 6: Deep Neural Networks

Lecture 1: Internals of a 2 layer Neural Network

Lecture 2: Understanding Computational Graphs

Lecture 3: Updating Parameters Effectively

Lecture 4: Understanding the Importance of Vectorization

Lecture 5: Summary of Back-propagation and Forward-propagation

Lecture 6: Initializing Parameters Effectively

Lecture 7: Understanding Layers and Units

Lecture 8: Understanding the Shapes

Lecture 9: Understanding Broadcasting in Programming

Chapter 7: Improving Neural Networks with Regularization Techniques

Lecture 1: Overfitting and Underfitting

Chapter 8: Building a Complete Neural Network Library for Predicting Handwritten Numbers

Lecture 1: Coding : Defining our Neural Network Structure

Chapter 9: Building Our Neural Network Library Utility Functions

Lecture 1: Coding : Defining our Data Object Structure

Lecture 2: Coding : Implementing a Function to Read Data From a File

Lecture 3: Coding : Implementing a Function to Parse our Data

Lecture 4: Coding : Implementing more Utility Functions

Chapter 10: Building Our Neural Network Library Engine

Lecture 1: Coding : Implementing the Forward Propagation Function

Lecture 2: Coding : Implementing the Back Propagation Function

Lecture 3: Coding : Implementing the NNPredict Function

Lecture 4: Coding : Implementing the NNBuild and NNTrain Functions

Lecture 5: Coding : Implementing the NNSaveModel and NNLoadModel Functions

Lecture 6: Coding : Implementing the NNPrint Function

Chapter 11: Testing our Neural Network Library

Lecture 1: Coding : Training a Model to Predict Handwritten Digits

Lecture 2: Coding : Testing our Model

Lecture 3: Coding : Running Inference with our Model

Chapter 12: Closing

Lecture 1: Closing Remarks