Skip to main content

Introduction to Deep Learning in Python

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

Start Course for Free
4 Hours17 Videos50 Exercises213,502 Learners3500 XPDeep Learning TrackMachine Learning Fundamentals TrackMachine Learning Scientist Track

Create Your Free Account

GoogleLinkedInFacebook

or

By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA. You confirm you are at least 16 years old (13 if you are an authorized Classrooms user).

Loved by learners at thousands of companies

Course Description

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.

  1. 1

    Basics of deep learning and neural networks

    Free

    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.

    Play Chapter Now
    Introduction to deep learning
    50 xp
    Comparing neural network models to classical regression models
    50 xp
    Forward propagation
    50 xp
    Coding the forward propagation algorithm
    100 xp
    Activation functions
    50 xp
    The Rectified Linear Activation Function
    100 xp
    Applying the network to many observations/rows of data
    100 xp
    Deeper networks
    50 xp
    Forward propagation in a deeper network
    50 xp
    Multi-layer neural networks
    100 xp
    Representations are learned
    50 xp
    Levels of representation
    50 xp
  2. 2

    Optimizing a neural network with backward propagation

    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.

    Play Chapter Now
    The need for optimization
    50 xp
    Calculating model errors
    50 xp
    Understanding how weights change model accuracy
    50 xp
    Coding how weight changes affect accuracy
    100 xp
    Scaling up to multiple data points
    100 xp
    Gradient descent
    50 xp
    Calculating slopes
    100 xp
    Improving model weights
    100 xp
    Making multiple updates to weights
    100 xp
    Backpropagation
    50 xp
    The relationship between forward and backward propagation
    50 xp
    Thinking about backward propagation
    50 xp
    Backpropagation in practice
    50 xp
    A round of backpropagation
    50 xp
  3. 3

    Building deep learning models with keras

    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.

    Play Chapter Now
    Creating a keras model
    50 xp
    Understanding your data
    50 xp
    Specifying a model
    100 xp
    Compiling and fitting a model
    50 xp
    Compiling the model
    100 xp
    Fitting the model
    100 xp
    Classification models
    50 xp
    Understanding your classification data
    50 xp
    Last steps in classification models
    100 xp
    Using models
    50 xp
    Making predictions
    100 xp
  4. 4

    Fine-tuning keras models

    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.

    Play Chapter Now
    Understanding model optimization
    50 xp
    Diagnosing optimization problems
    50 xp
    Changing optimization parameters
    100 xp
    Model validation
    50 xp
    Evaluating model accuracy on validation dataset
    100 xp
    Early stopping: Optimizing the optimization
    100 xp
    Experimenting with wider networks
    100 xp
    Adding layers to a network
    100 xp
    Thinking about model capacity
    50 xp
    Experimenting with model structures
    50 xp
    Stepping up to images
    50 xp
    Building your own digit recognition model
    100 xp
    Final thoughts
    50 xp

In the following tracks

Deep LearningMachine Learning FundamentalsMachine Learning Scientist

Datasets

Hourly wagesMNISTTitanic

Collaborators

hugobowneHugo Bowne-AndersonyashasYashas Roy

Prerequisites

Supervised Learning with scikit-learn
Dan Becker Headshot

Dan Becker

Data Scientist and contributor to Keras and TensorFlow libraries

Dan Becker is a data scientist with years of deep learning experience. He has contributed to the Keras and TensorFlow libraries, finishing 2nd (out of 1353 teams) in the $3million Heritage Health Prize competition, and supervised consulting projects for 6 companies in the Fortunate 100. He previously worked as a data scientist at Google. Now he is the CEO and co-founder of Decision.ai, which helps companies apply their machine learning models to make better real-world decisions.
See More

What do other learners have to say?

I've used other sites—Coursera, Udacity, things like that—but DataCamp's been the one that I've stuck with.

Devon Edwards Joseph
Lloyds Banking Group

DataCamp is the top resource I recommend for learning data science.

Louis Maiden
Harvard Business School

DataCamp is by far my favorite website to learn from.

Ronald Bowers
Decision Science Analytics, USAA