Welcome to A Gentle Introduction to Deep Learning Using Keras.
Keras is a powerful easy-to-use Python library for developing and evaluating deep learning models.
It wraps the efficient numerical computation libraries Theano and TensorFlow and allows you to define and train neural network models in a few short lines of code.
In this course, we are going to build an end-to-end Python machine learning project. You’ll learn how to use Keras to build and tune a deep neural network.
Keras is quickly becoming the de facto tool to do deep learning in Python, especially for beginners. Its minimalist, modular approach makes it simple to get deep neural networks up and running.
A Jupyter notebook is a web app that allows you to write and annotate Python code interactively. It's a great way to experiment, do research, and share what you are working on.
In this course all of the tutorials will be created using jupyter notebooks. In the preview lessons we install Python. Check them out. They are completely free.
We will also gently introduce you to the vernacular of deep learning. For example, a deep neural network is simply a neural network with more than one hidden layer. That’s it.
Actually, a hidden layer really means "not an input or an output."
Why all the hype around deep learning? While much of the hype in the IT world is just that, the hype around deep learning may be the real thing. Recently, deep learning models have been outperforming every other kind of machine learning model.
You’ll get hands on experience with the process of machine learning. The process involves importing data, cleaning the data, training and testing, pre-processing and feature engineering.
We are going to define new terms but we will skip the math and theory for now.
Thanks for your interest in A Gentle Introduction to Deep Learning Using Keras.
See you in the course!!!!
This is an introduction to the course.
What is Keras and what are we going to learn?
We need micro goals in order measure our learning.
What are we going to learn in the course.
While this isn't a comprehensive definition it will give you a solid starting point in defining what deep learning really is.
What is prediction analysis.
Let's define in it relation to our every day life.
This is our IDE.
It's super easy to learn.
Let's get it installed here.
This lecture will show you where to put the Jupyter Notebook and why I included 2 .csvs for the course.
This will have the downloads for the course.
We need to import our libraries in order to use their functionality.
Let's load out data set in this lecture.
Let's create an array in order to split out our variables.
In this lecture let's build the core Keras model.
In this brief lecture let's compile the model.
Let's fit our model to our data.
Let's walk through the process running the entire model.
Let's attempt to squeeze some more performance out of our model.
I've been a production SQL Server DBA most of my career.
I've worked with databases for over two decades. I've worked for or consulted with over 50 different companies as a full time employee or consultant. Fortune 500 as well as several small to mid-size companies. Some include: Georgia Pacific, SunTrust, Reed Construction Data, Building Systems Design, NetCertainty, The Home Shopping Network, SwingVote, Atlanta Gas and Light and Northrup Grumman.
Experience, education and passion
I learn something almost every day. I work with insanely smart people. I'm a voracious learner of all things SQL Server and I'm passionate about sharing what I've learned. My area of concentration is performance tuning. SQL Server is like an exotic sports car, it will run just fine in anyone's hands but put it in the hands of skilled tuner and it will perform like a race car.
Certifications are like college degrees, they are a great starting points to begin learning. I'm a Microsoft Certified Database Administrator (MCDBA), Microsoft Certified System Engineer (MCSE) and Microsoft Certified Trainer (MCT).
Born in Ohio, raised and educated in Pennsylvania, I currently reside in Atlanta with my wife and two children.