Data Science: Deep Learning in Python

Note: This post contains affiliate links and I may be compensated if you click on them.

The Udemy course “Data Science: Deep Learning in Python” is a guide for writing your own neural network in Python and Numpy, and how to do it in Google’s TensorFlow. You will learn how to code a neural network from scratch in Python and Numpy, and how to code a neural network using Google’s TensorFlow. You will learn the various terms related to neural networks, such as “activation”, “backpropagation” and “feedforward”, the different types of neural networks and the different types of problems they are used for. You will also learn to derive the backpropagation rule from first principles and create a neural network with an output that has K > 2 classes using Softmax.

Data Science: Deep Learning in Python Course Content

This course focuses on “how to build and understand”, not just “how to use”. It will teach you how to visualize what’s happening in the model internally. It will get you started in building your FIRST artificial neural network using deep learning techniques. You will build full-on non-linear neural networks right out of the gate using Python and Numpy, and implement a neural network using Google’s new TensorFlow library.

The course provides you with many practical examples so that you can really see how deep learning can be used on anything. Throughout the course, we’ll do a course project, which will show you how to predict user actions on a website given user data like whether or not that user is on a mobile device, the number of products they viewed, how long they stayed on your site, whether or not they are a returning visitor, and what time of day they visited.

The course comprises 55 Lectures organized into the following sections:

What is a neural network?
Classifying more than 2 things at a time
Training a neural network
Practical Machine Learning
TensorFlow, exercises, practice, and what to learn next
Project: Facial Expression Recognition
Appendix

Requirements

How to take partial derivatives and log-likelihoods (ex. finding the maximum likelihood estimations for a die)
Install Numpy and Python (approx. latest version of Numpy as of Jan 2016)
Don’t worry about installing TensorFlow, we will do that in the lectures.
Being familiar with the content of the instructor’s logistic regression course (cross-entropy cost, gradient descent, neurons, XOR, donut) will give you the proper context for this course.