Skip to main content

Advanced Deep Learning with Keras

4.6+
13 reviews
Intermediate

Build multiple-input and multiple-output deep learning models using Keras.

Start Course for Free
4 Hours13 Videos46 Exercises28,337 Learners

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.

Loved by learners at thousands of companies

Course Description

This course shows you how to solve a variety of problems using the versatile Keras functional API. You will start with simple, multi-layer dense networks (also known as multi-layer perceptrons), and continue on to more complicated architectures. The course will cover how to build models with multiple inputs and a single output, as well as how to share weights between layers in a model. We will also cover advanced topics such as category embeddings and multiple-output networks. If you've ever wanted to train a network that does both classification and regression, then this course is for you!
  1. 1

    The Keras Functional API

    Free

    In this chapter, you'll become familiar with the basics of the Keras functional API. You'll build a simple functional network using functional building blocks, fit it to data, and make predictions.

    Play Chapter Now
    Keras input and dense layers
    50 xp
    Input layers
    100 xp
    Dense layers
    100 xp
    Output layers
    100 xp
    Build and compile a model
    50 xp
    Build a model
    100 xp
    Compile a model
    100 xp
    Visualize a model
    100 xp
    Fit and evaluate a model
    50 xp
    Fit the model to the tournament basketball data
    100 xp
    Evaluate the model on a test set
    100 xp
  2. 2

    Two Input Networks Using Categorical Embeddings, Shared Layers, and Merge Layers

    In this chapter, you will build two-input networks that use categorical embeddings to represent high-cardinality data, shared layers to specify re-usable building blocks, and merge layers to join multiple inputs to a single output. By the end of this chapter, you will have the foundational building blocks for designing neural networks with complex data flows.

    Play Chapter Now
    Category embeddings
    50 xp
    Define team lookup
    100 xp
    Define team model
    100 xp
    Shared layers
    50 xp
    Defining two inputs
    100 xp
    Lookup both inputs in the same model
    100 xp
    Merge layers
    50 xp
    Output layer using shared layer
    100 xp
    Model using two inputs and one output
    100 xp
    Predict from your model
    50 xp
    Fit the model to the regular season training data
    100 xp
    Evaluate the model on the tournament test data
    100 xp
  3. 3

    Multiple Inputs: 3 Inputs (and Beyond!)

    In this chapter, you will extend your 2-input model to 3 inputs, and learn how to use Keras' summary and plot functions to understand the parameters and topology of your neural networks. By the end of the chapter, you will understand how to extend a 2-input model to 3 inputs and beyond.

    Play Chapter Now
    Three-input models
    50 xp
    Make an input layer for home vs. away
    100 xp
    Make a model and compile it
    100 xp
    Fit the model and evaluate
    100 xp
    Summarizing and plotting models
    50 xp
    Model summaries
    100 xp
    Plotting models
    100 xp
    Stacking models
    50 xp
    Add the model predictions to the tournament data
    100 xp
    Create an input layer with multiple columns
    100 xp
    Fit the model
    100 xp
    Evaluate the model
    100 xp
  4. 4

    Multiple Outputs

    In this chapter, you will build neural networks with multiple outputs, which can be used to solve regression problems with multiple targets. You will also build a model that solves a regression problem and a classification problem simultaneously.

    Play Chapter Now
    Two-output models
    50 xp
    Simple two-output model
    100 xp
    Fit a model with two outputs
    100 xp
    Inspect the model (I)
    100 xp
    Evaluate the model
    100 xp
    Single model for classification and regression
    50 xp
    Classification and regression in one model
    100 xp
    Compile and fit the model
    100 xp
    Inspect the model (II)
    100 xp
    Evaluate on new data with two metrics
    100 xp
    Wrap-up
    50 xp

In the following tracks

Deep Learning in PythonMachine Learning Scientist with Python

Datasets

Basketball dataBasketball models

Collaborators

Sumedh Panchadhar

Prerequisites

Introduction to Deep Learning in Python
Zachary Deane-Mayer HeadshotZachary Deane-Mayer

VP, Data Science at DataRobot

Zach is a Data Scientist at DataRobot and co-author of the caret R package. He's fascinated by predicting the future and spends his free time competing in predictive modeling competitions. He's currently one of top 500 data scientists on Kaggle and took 9th place in the Heritage Health Prize as part of the Analytics Inside team.
See More

Don’t just take our word for it

*4.6
from 13 reviews
77%
15%
0%
8%
0%
Sort by
  • Hsing-chuan H.
    6 months

    A good quick overview of Advanced DL

  • Jorge C.
    6 months

    Great intro to Functional API

  • arwinder m.
    6 months

    Great course.

  • Jean-Pierre R.
    6 months

    I really did love this course, and it covers a good chunk of the advanced and applicable topics in deep learning. I wish it was longer and had more.

  • Aldo M.
    6 months

    cool

    • Loading ...

"A good quick overview of Advanced DL"

Hsing-chuan H.

"Great intro to Functional API"

Jorge C.

"Great course."

arwinder m.

Join over 11 million learners and start Advanced Deep Learning with Keras today!

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.