Building Deep Neural Networks in Keras Master Class
4.2 (9 ratings)
Instead of using a simple lifetime average, Udemy calculates a course's star rating by considering a number of different factors such as the number of ratings, the age of ratings, and the likelihood of fraudulent ratings.
53 students enrolled
Wishlisted Wishlist

Please confirm that you want to add Building Deep Neural Networks in Keras Master Class to your Wishlist.

Add to Wishlist

Building Deep Neural Networks in Keras Master Class

A Practical Guide to Tuning Deep Learning Models with Keras
4.2 (9 ratings)
Instead of using a simple lifetime average, Udemy calculates a course's star rating by considering a number of different factors such as the number of ratings, the age of ratings, and the likelihood of fraudulent ratings.
53 students enrolled
Created by Mike West
Last updated 6/2017
English
Curiosity Sale
Current price: $10 Original price: $25 Discount: 60% off
30-Day Money-Back Guarantee
Includes:
  • 1 hour on-demand video
  • 10 Articles
  • 2 Supplemental Resources
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
What Will I Learn?
  • You'll be able to build deep learning models using Keras.
  • You'll learn how to evaluate the performance of neural networks built using Keras.
  • You'll build model an incorporate SciKit-Learn for general purpose machine learning.
  • You'll understand how to tune Keas layers on different network topologies.
  • You'll know how to build a model baseline for performance comparison.
  • You'll code several neural networks from the ground up in Python using Keras.
View Curriculum
Requirements
  • You'll need a basic understanding of Artificial Neural Networks.
  • You'll need a basic understanding of Python.
Description

Recent Reviews of Similar Course:

Pure excellence from the presenter!!!! Great content!!! Buy this course, you won't regret it.Social Scientist Redvers Crooks

Almost perfect, I feel like there can be more to the course but it is short and sweet. -- Christopher Brashear

Course Description: 

Welcome to Building Deep Neural Networks in Keras Master Class. In this course, we are going to build an then tune Keras models. 

The area of study which involves extracting knowledge from data is called as Data Science and people practicing in this field are called as Data Scientists.

Keras is a relatively new library in Python designed for building neural networks.  The library sits on top of Theano and Tensorflow. This means it can take advantage of the computational speed and efficiency of the two yet offer a high level, comfortable interface that data scientists using Python are used to.

I’m using the term “master class” to denote that this isn’t an introductory course. I do expect the student to know some Python and basic neural network topology.  

The top career in the world right now is that of the data scientist and the top machine learning tool right now is deep learning. Another name for deep learning is artificial neural networks. Artificial neural networks is the term you’ll see in academia and deep learning the more commercial term. Throughout the course, I will use the two interchangeably.

We are going to cover the five major steps involved in building models in Keras. Our first step will be loading data, secondly, we will be defining a model, thirdly we will be compiling a model, fourthly,  fitting the model and finally evaluating the model.  After we build the model we are going to delve deeper into evaluating the performance of keras models. Deep learning models have many buttons and knobs that can be tweaked and altered to deliver more accurate results.

In the course, we will skip the math and focus on data cleansing and model building. The two core skills you’ll need for a career in applied machine learning. Applied machine learning simply means you go to work and the models you build don’t end up in papers they end up in real world production environments.


                                                               **Five Reasons to Take this Course**

1) Wide Adoption of Keras

Deep learning is the single hottest niche in the machine learning field.  Because Keras is written for Python it has a high level interface allows for ease of use for novice as well as more experienced users. It's quickly becoming the standard for rapid model deployment in the applied world. 

2) Occam's Razor Approach to Teaching

Less is almost always more.  If you're serious about deep learning as a career you don't need or want your hand held for long periods of time.  You want the core of any subject and then you want to get your hands dirty. My courses are short and to the point. You don't have time for filler and I don't believe in adding it. 

3) Real World Instructor Experience

I've been working with databases for over two decades and was building predictive analytic models when it was called data mining. There's really no difference between data mining and applied predictive analytics. Much of what you'll be doing as a data scientist or machine learning engineer is cleansing data and you'll find very few who have more data experience than DBAs. 

4) Line by Line Code Explanation 

In all my machine learning courses I explain every line of code.  Python is very easy to learn but there's still a lot of nuances you'll need to know before mastering it specific to machine learning. 

5) Limited Selection of Courses Specific to Keras

There are few courses specific to Keras. Even though it's been widely adopted, much like it's frame work library TensorFlow, very few have real world hands on experience with it. While I can't show you my production models but I can show you what I've learned building them. 

Thanks for your interest in Deep Learning with Keras Masterclassand we will see you in the course. 

Who is the target audience?
  • If you are interested in building and tuning deep learning models in Keras then this course is for you.
  • Please be aware this is not a course for beginners.
Students Who Viewed This Course Also Viewed
Curriculum For This Course
35 Lectures
01:22:29
+
Introduction
9 Lectures 16:54

Let's introduce the course. 

What's the course about? 

Preview 01:48

What is Keras? 

Who created it? 

What does high level really mean? 

Let's find out in this lesson. 

Preview 03:15

In this lesson let's discuss what we are going to learn. 

Who is the course for? 

It's not a beginners course although it's not advanced either. 

Preview 01:15

Let's install Python. 

Preview 02:55

You'll need to have Python installed. 

I installed Python using the Anaconda distribution and I'd suggest you do the same. 

Once you have Python up and running then this lecture will show you how to install Keras. 

Preview 02:18

Keras sits on top of one of two libraries and uses them for numerical computations. 

In this lesson let's find out what they are and how to change them. 

Switching Backends
03:01

This lesson is a brief question and answer lecture about the course, deep learning and machine learning in general. 

Instructor Question and Answer
01:29

Course Downloads
00:04

Summary
00:49

Quiz
5 questions
+
Keras Modeling Process
9 Lectures 26:45

Prior to importing our data we need to import our libraries and set a random seed. 

Let's learn how to do that in this lesson. 

Import Libraries
03:05

In this lesson let's load our data. 

I'll also show you how to download the data and put it in your own text file. 

Load Data
05:22

In this lesson let's learn about the core lines of code needed to build the model and the layers of our neural network. 

Define Model
03:18

Let's walk through the Keras model line by line. 

This code is the core of every Keras model. 

Anatomy of the Code
04:28

This can be difficult to understand but it's very important in deep learning. 

Let's define bias graphically. 

Defining Bias
01:09

Let's compile our model. 

Compile Model
03:41

In this short less we will fit our data to the model. 

This is quick and easy. 

Fit Model
02:39

Let's score the model and see how we did. 

Evaluate Model
01:54

Summary
01:08

Quiz
11 questions
+
Evaluating Model Performance
7 Lectures 15:56

In this lesson let's ensure we know the difference between parameter and variable. 

We are going to be passing a lot of Hyper Parameters into our models in the upcoming lesson so it's very import we know exactly what a parameter is. 

Parameter VS. Variable
02:34

In this lesson we will learn about automated model validation. 

The great part about this is there's not one line of additional code. 

We just alter an existing line and off we go. 

Automatic Validation
02:25

Let's manually validate our model. 

This is also easily done by adding a couple of line of code. 

You'll quickly see just why Python is the gold standard in machine learning. 

Manual Validation
02:59

It's the gold standard in model validation but not normally used on deep learning models because of the computational cost. 

Let's learn what it is in the brief lesson. 

What is K-Fold Validation
01:36

Not often used in deep learning models because of the computational impact it adds. 

However, k-fold is the gold standard outside of the deep learning world and we can use it inside Keras. 

Let's learn how. 

Applying K-Fold Validation
02:06

Grid search is a model hyperparameter optimization technique.

In scikit-learn this technique is provided in the GridSearchCV class. 

In this lesson let's learn how to apply it. 

Grid Search
03:24

Summary
00:52

Quiz
10 questions
+
Use Cases
7 Lectures 18:46

In this lecture let's build a Keras model for a binary classifier. 

We will use a familiar data set. 

The data set will be included in the downloads so you don't have to hunt it down. 

Building and Tuning a Binary Classification Model
04:51

We can force a type of feature extraction by the network by restricting the representational space in the first hidden layer.

The translation for this is we can remove the number of neurons from our model. 

In this lesson let's reduce the neurons in our first hidden layer. 

Evaluate A Smaller Network
01:09

In this lecture let's add another layer to our network. 

We should see a significant boost in performance. 

Evaluate a Larger Network
01:23

One hot encoding is a lot easier to understand when we can represent it visually. 

In this lesson let's visual how machine learning uses one hot encoding. 

One Hot Encoding Visually
01:17

In this lesson let's build a multi-class classification model. 

Building and Tuning Multi-Class Classification Model
05:56

In this lecture let's save our work. 

Building larger neural networks can be time consuming. 

Use Checkpoints to Save the Best Model
03:25

Summary
00:45

Quiz
8 questions
+
Additions
3 Lectures 04:30

Let's learn a few questions you might see on an interview specific to Keras. 

Even though Keras is fairly new you'll need to answer questions about how to build production ready models. 

Keras Interview Questions
04:14

Here are a few free resources you can use to expand you Keras knowledge. 

Free Keras Resources
00:07

Just a quick thank you from me to you for taking my course. 

Conclusion
00:09
About the Instructor
Mike West
4.2 Average rating
2,606 Reviews
43,103 Students
40 Courses
SQL Server and Machine Learning Evangelist

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

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).

Personal

Born in Ohio, raised and educated in Pennsylvania, I currently reside in Atlanta with my wife and two children.