In this chapter, you'll become familiar with the fundamental concepts and terminology used in deep learning, and understand why deep learning techniques are so powerful today. You'll build simple neural networks and generate predictions with them.

Introduction to deep learning

Comparing neural network models to classical regression models

Forward propagation

Coding the forward propagation algorithm

Activation functions

The Rectified Linear Activation Function

Applying the network to many observations/rows of data

Deeper networks

Forward propagation in a deeper network

Multi-layer neural networks

Representations are learned

Levels of representation

Basics of deep learning and neural networks

Learn how to optimize the predictions generated by your neural networks. You'll use a method called backward propagation, which is one of the most important techniques in deep learning. Understanding how it works will give you a strong foundation to build on in the second half of the course.

The need for optimization

Calculating model errors

Understanding how weights change model accuracy

Coding how weight changes affect accuracy

Scaling up to multiple data points

Gradient descent

Calculating slopes

Improving model weights

Making multiple updates to weights

Backpropagation

The relationship between forward and backward propagation

Thinking about backward propagation

Backpropagation in practice

A round of backpropagation

Optimizing a neural network with backward propagation

In this chapter, you'll use the Keras library to build deep learning models for both regression and classification. You'll learn about the Specify-Compile-Fit workflow that you can use to make predictions, and by the end of the chapter, you'll have all the tools necessary to build deep neural networks.

Creating a Keras model

Understanding your data

Specifying a model

Compiling and fitting a model

Compiling the model

Fitting the model

Classification models

Understanding your classification data

Last steps in classification models

Using models

Making predictions

Building deep learning models with keras

Learn how to optimize your deep learning models in Keras. Start by learning how to validate your models, then understand the concept of model capacity, and finally, experiment with wider and deeper networks. 

Understanding model optimization

Diagnosing optimization problems

Changing optimization parameters

Model validation

Evaluating model accuracy on validation dataset

Early stopping: Optimizing the optimization

Experimenting with wider networks

Adding layers to a network

Thinking about model capacity

Experimenting with model structures

Stepping up to images

Building your own digit recognition model

Final thoughts

Fine-tuning keras models

Hourly wages

MNIST

Titanic

Deep learning is the machine learning technique behind the most exciting capabilities in diverse areas like robotics, natural language processing, image recognition, and artificial intelligence, including the famous AlphaGo. In this course, you'll gain hands-on, practical knowledge of how to use deep learning with Keras 2.0, the latest version of a cutting-edge library for deep learning in Python.

<h2>Discover Deep Learning Applications </h2>
Deep learning is the machine learning technique behind the most exciting capabilities in robotics, natural language processing, image recognition, and artificial intelligence. In this 4-hour course, you’ll gain hands-on practical knowledge of how to apply your Python skills to deep learning with the Keras 2.0 library.
<br><br>
<h2>Explore Keras Models with a Library Contributor</h2>
Taught by ex-Google data scientist and Keras contributor, Dan Becker, this deep learning course explores neural network models and how you can generate predictions with them. The first chapters will grow your understanding of both forward and backward propagation and how they work in practice.
<br><br>
Keras library is a Python library that can help you develop and review deep learning models. Like many Python libraries, it's free, open-source and very user friendly. You’ll start by creating a Keras model and will learn how to compile, fit, and classify it before making predictions. Once you’ve completed this course, you’ll have all the tools you need to build deep neural networks and start experimenting with wider and deeper networks over time.
<br><br>
<h2>Delve Further into Deep Learning</h2>
This course is part of several machine learning and deep learning tracks, offering you clear pathways to build your skills and experience in this area once you’ve completed the introductory course, whether you want to complete a personal project or move towards a career as a Machine Learning Scientist.

Supervised Learning with scikit-learn

Discover how you can use deep learning to run natural language processing, image recognition, and artificial intelligence with Python package, Keras 2.0.

Introduction to Deep Learning in Python

Learn the fundamentals of neural networks and how to build deep learning models using Keras 2.0 in Python. 

Comparing neural network models to classical regression models

Introduction to Deep Learning in Python

Hands-on interactive exercise