Deep Learning with R in Motion
Rick J. Scavetta
  • Course duration: 1h 27m
    Estimated full duration: 8h
  • MEAP began May 2018
  • Publication in August 2018 (estimated)

Deep Learning with R in Motion teaches you to apply deep learning to text and images using the powerful Keras library and its R language interface. This liveVideo course builds your understanding of deep learning up through intuitive explanations and fun, hands-on examples!

Table of Contents detailed table of contents

Getting Started

Welcome to the Video Series

What is Deep Learning?

The Landscape of Deep Learning

The Landscape of Machine Learning

The Two Golden Hypotheses

The 4 Types of Machine Learning

MNIST Case Study

Unit Introduction

The MNIST dataset

A first look at a neural network

The 4 steps of Deep Learning, part 1

The 4 steps of Deep Learning, part 2

The Uses of Derivatives

From Derivatives to Gradients

Momentum in Mini-batch Stochastic Gradient Descent

The 4 steps of Deep Learning, part 3

Basic Model Evaluation

Three Case Studies for Deep Learning

The Reuters dataset: Single-label, Multi-class Classification Revisited

The Reuters dataset: Coding run-through

The Reuters dataset: Take-home Messages

The IMDC Dataset: Binary Classification

The IMDC Dataset: Coding run-through

The IMDC Dataset: Take-home Messages

The Boston Housing Dataset: Regression

The Boston Housing Dataset: Coding run-through

The Boston Housing Dataset: Take-home Messages

Putting It All Together: Overfitting and the Universal Workflow

Summary of Analytical Questions we’ve seen so far

Chapter Intro: Overfitting

Overcoming Overfitting I - More data

Overcoming Overfitting II - Model Capacity

Overcoming Overfitting III - Weight Regularization

Overcoming Overfitting IV - Adding Dropout

The Machine Learning Universal Workflow

Computer Vision

Setting up: GPU vs CPU

Setting up an EC2 instance

Chapter Intro

Dataset 5 - The Cat & Dog show, Image Classification

Intro to Convnets

The advantages of pre-trained Convnets

The Landscape of pre-trained Convnets

Coding convnets

Convnets with small datasets

Pre-trained convnets

Visualizing convnets

Chapter Wrap-up

Text & Sequences

Chapter Intro

Varieties of Tokenizations

Analysis Problem 6 - Text Classifications

Pre-trained Word embeddings

Recurrent Neural Networks

Dataset 6 - The Jena weather data & Temperature Forecasting

Covnets vs RNNs

One-hot encoding

Coding recurrent neural networks

Advanced recurrent neural networks

Chapter Wrap-up

Best Practices

Chapter Intro

Idiosyncratic structures

The Keras functional API

Monitoring Models during training

Visualising metrics with TensorBoard

Chapter Wrap-up

Generative Deep Learning

Chapter Intro

Generative recurrent networks in the wild

Generative adversarial networks in the wild

What are generative recurrent networks?

Intro to 4 Case Studies

Character-level LSTM run-through

Reproducing DeepDream

Neural style transfer run-through

What are variational autoencoders?

Generating images

GAN run-through

Sequence processing with convnets

Generating images

Chapter Wrap-up


Chapter Intro

Deep learning in the landscape of Machine Learning

Technology Review

The universal machine-learning workflow

A review of network architectures

Possibilities and Limitations of Deep Learning

Book & Video Wrap-up

About the subject

Machine learning has made remarkable progress in recent years. Deep learning systems have revolutionized image recognition, natural-language processing, and other applications for identifying complex patterns in data. The Keras library provides data scientists and developers working in R a state-of-the-art toolset for tackling deep learning tasks!

About the video

See it. Do it. Learn it! The keras package for R brings the power of deep learning to R users. Deep Learning with R in Motion locks in the essentials of deep learning and teaches you the techniques you'll need to start building and using your own neural networks for text and image processing.

Instructor Rick Scavetta takes you through a hands-on ride through the powerful Keras package, a TensorFlow API. You'll start by digging into case studies for how and where to use deep learning. Then, you'll master the essential components of a deep learning neural network as you work hands-on through your first examples. You'll continue by exploring dense and recurrent neural networks, convolutional and generative networks, and how they all work together.

And that's just the beginning! You'll go steadily deeper, making your network more robust and efficient. As your work through each module, you'll train your network and pick up the best practices used by experts like expert instructor Rick Scavetta, Keras library creator and author of Deep Learning in Python François Chollet, and JJ Allaire, founder of RStudio, creator of the R bindings for Keras, and coauthor of Deep Learning in R! You'll beef up your skills as you practice with R-based applications in computer vision, natural-language processing, and generative models, ready for the real-world.

This liveVideo course can be used by itself or along with the Manning books Deep Learning with R and Deep Learning with Python. All examples are in R.


You'll need intermediate R programming skills. No previous experience with machine learning or deep learning is assumed.

What you will learn

  • The 4 steps of Deep Learning
  • Using R with Keras and TensorFlow
  • Working with the Universal Workflow
  • Computer vision with R
  • Recurrent neural networks
  • Everyday best practices
  • Generative deep learning

About the instructor

Rick Scavetta is a biologist, workshop trainer, freelance data scientist, cofounder of Science Craft, and founder of Scavetta Academy, companies dedicated to helping scientists better understand and visualize their data. Rick's practical, hands-on exposure to a wide variety of datasets has informed him of the many problems scientists face when trying to visualize their data.

Deep Learning with Python by François Chollet and Deep Learning with R adapted by J.J. Allaire are both available at in pBook, eBook, and liveBook formats.