Skip to content
Tutorial: Deep learning in R using Keras
Branch: master
Clone or download
Latest commit 10462a8 Jun 1, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
binder move binder files into subdirectory Dec 5, 2018
cloudml
data-raw/dog-human parts 1 and 2 complete. slide updates forthcoming Dec 6, 2018
docs Review: key concepts slide move Apr 22, 2019
.gitignore
Deep-Learning-in-R.Rproj switch to personal repo Oct 8, 2018
README.md fix typo in readme Jun 1, 2019
part1.Rmd Merge branch 'master' of github.com:dlab-berkeley/Deep-Learning-in-R Apr 22, 2019
part2.Rmd
part3.Rmd
part4_cloudml.Rmd
participant-instructions.Rmd
participant-instructions.md remove extra header info Mar 26, 2019

README.md

Deep Learning in R

This is the repository for D-Lab’s six-hour Introduction to Deep Learning in R workshop. View the associated slides here.

Binder

Objectives

Convey the basics of deep learning in R using keras on image datasets. Students are empowered with a general grasp of deep learning, example code that they can modify, a working computational environment, and resources for further study.

Content outline

  • Installation
    • R and RStudio
    • Keras and Tensorflow
    • Helper packages
  • What is “deep” learning?
  • Understanding the dataset
  • Dataset splitting: training, test, cross-validation
    • Defining moving parts of a deep learning model
    • Understanding a loss function, activation function, and metrics
    • Performance evaluation
  • Part 1-2
    • MNIST 0-9 hand-written digit example
    • Dogs or humans?
  • Part 3-4
    • Pre-trained models + fine-tuning
    • X-ray classification: abdominal vs. chest classification
    • Google Cloud Machine Learning

Prerequisites

This is an advanced level workshop. Participants should be intermediate R users and have had some prior exposure to machine learning.

We assume the following background:

  • D-Lab's Machine Learning in R introduction (4 hours)
  • Or, comparable experience/training, assuming familiarity with:
    • Basic R syntax
    • statistical concepts such as mean and standard deviation
    • Train/test splitting and cross-validation
    • Dataset cleaning
    • Overfitting / underfitting
    • Hyperparameter customization

If you are not comfortable installing packages, writing your own R code, and using RStudio, this will not be a good workshop for you.

Technology requirements

Please bring a laptop with the following:

Getting Started

Be sure to follow the install instructions to get started. This process can take about 30 minutes, so be sure to try and do this before class.

Resources

You can’t perform that action at this time.