{ C Language } Deep Learning From Ground Up™

Are you tired of hearing about deep learning and not knowing how to properly get started?

Do you already know how to write basic c code?

Here’s an overview of what you’re getting in this ground up course...

Introduction to Neural Networks:

This course completely demystifies Neural Networks. The course starts from the complete basics as if you were a 5 year old. You will master and develop your own building blocks for deep neural networks. Building blocks such as :

-The Single-Input-Single-Output Neural Network

-The Single-Input-Multiple-Output Neural Network

-The Multiple-Input-Single-Output Neural Network

-The Multiple-Input-Multiple-Output Neural Network

-The Hidden Layer Neural Network

The internals of a deep learning engine:

After mastering the fundamental building blocks of neural networks, the course then goes on to treat the internals of a deep learning engine from a first principles approach. We shall look at topics such as:

-Gradient Descent

-The Loss Function

-The Activation Function

-Forward Propagation

-Back Propagation

-Training

-Computational Graphs

-Weights Normalization and Randomization

… and much more.

Building your own a Complete Neural Network Library for Predicting Handwritten Numbers.

The latter part of the course puts everything together to develop a complete neural network library for predicting handwritten numbers. You shall be guided step-by-step throughout this process. We shall start by implementing the utilities functions and data structures. Specifically, we shall:

-Define our neural network’s data structure

-Define our data object structure

-Implement a function for reading data from a file

-Implement a function for parsing the data

Then we shall go on to implement the various modules of the neural network engine. We shall implement:

-The Forward Propagation function

-The Back Propagation function

-The Prediction function

-The Training function

Once all of this is thoroughly implemented we then go on to….

-Train our model

-Test our model by running some predictions.