https://github.com/wlandau/rpharma2019
Repo for the Workshop: "Artificial neural networks in R with Keras and TensorFlow" at the 2nd annual R in Pharma Conference Aug. 21st-23rd 2019 at Harvard University, Cambridge, US
https://github.com/wlandau/rpharma2019
Last synced: about 1 month ago
JSON representation
Repo for the Workshop: "Artificial neural networks in R with Keras and TensorFlow" at the 2nd annual R in Pharma Conference Aug. 21st-23rd 2019 at Harvard University, Cambridge, US
- Host: GitHub
- URL: https://github.com/wlandau/rpharma2019
- Owner: wlandau
- Created: 2019-08-21T12:42:53.000Z (over 5 years ago)
- Default Branch: main
- Last Pushed: 2020-10-27T16:02:41.000Z (over 4 years ago)
- Last Synced: 2025-02-14T13:15:14.720Z (3 months ago)
- Language: HTML
- Homepage: http://rinpharma.com/
- Size: 7.5 MB
- Stars: 0
- Watchers: 2
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.Rmd
Awesome Lists containing this project
README
---
title: "Workshop: Artificial neural networks in R with Keras and TensorFlow"
output: github_document
---
```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```
## Interested in a walk-through of this workshop?
Please feel free to [get in touch](https://nordicdatalab.dk/en/#contact). This workshop was created and hosted by [Leon Eyrich Jessen](https://twitter.com/jessenleon).
## Introduction
This is the GitHub repository for the Workshop: "Artificial neural networks in R with Keras and TensorFlow" at [The second annual R/Pharma conference held August 21, 22, and 23, 2019, Harvard University, Cambridge, US](http://rinpharma.com/)
Everything you need to know can be found at the RStudio page on [R Interface to TensorFlow](https://tensorflow.rstudio.com/). Here you can also find more on [keras](https://tensorflow.rstudio.com/keras/), with [examples](https://tensorflow.rstudio.com/keras/articles/examples/) and [invited blog posts](https://blogs.rstudio.com/tensorflow/)
## Getting started - Complete the following 10 easy steps, to be able to run the workshop
1. Go to [https://rstudio.cloud/](https://rstudio.cloud/) (Create an account if you do not have one)
2. Find the button "New Project" and click the arrow down symbol
3. Choose "New Project from Git Repo"
4. In the "URL of your Git repository", enter [https://github.com/leonjessen/RPharma2019](https://github.com/leonjessen/RPharma2019) and click "OK"
5. "Deploying Project" will now appear and after some time a new session is loaded
6. Name your project in the upper left corner, where it says "Your Workspace / Untitled Project <- Click to name you project"
7. In the lower right pane, you will now see all the workshop materials
8. Run the following commands in the console (left pane) to setup software environment:
```{r eval=FALSE, echo=TRUE}
install.packages("tidyverse")
install.packages("devtools")
devtools::install_github("rstudio/keras")
library(keras)
install_keras()
```
9. Return to [https://github.com/leonjessen/RPharma2019](https://github.com/leonjessen/RPharma2019), find and follow "Schedule Wednesday August 21st 2019"
10. Have fun!
## Schedule Wednesday August 21st 2019
At the workshop, the aim is to briefly introduce the participants to the theory of artificial neural networks and the follow this up with a series of interchanging brief talks and longer exercises aiming at building inital hands on experience. The schedule is as follows:
_(Please note the html preview currently seem not be functioning. All slides are available under 'Talks' in your RStudio session. Left-click on the .html file and choose 'View in Web Browser')_
- (08.40 - 08.55) [Brief talk: Introduction to Artificial Neural Networks](http://htmlpreview.github.io/?https://github.com/leonjessen/RPharma2019/blob/master/Talks/01_introduction_to_artificial_neural_networks.html)
- (08.55 - 09.20) [Exercise: Prototyping an ANN in R](Exercises/01_ann_prototype.md)
- (09.20 - 09.25) [Brief talk: Introduction to TensorFlow/Keras in R 1](http://htmlpreview.github.io/?https://github.com/leonjessen/RPharma2019/blob/master/Talks/02_introduction_to_keras_1.html)
- (09.25 - 09.45) [Exercise: TensorFlow Playground](Exercises/02_tensorflow_playground.md)
- (09.45 - 10.00) [Brief talk: Introduction to TensorFlow/Keras in R 2](http://htmlpreview.github.io/?https://github.com/leonjessen/RPharma2019/blob/master/Talks/03_introduction_to_keras_2.html)
- (10.00 - 10.10) [Brief talk: Session 1 Summary and Q&A](http://htmlpreview.github.io/?https://github.com/leonjessen/RPharma2019/blob/master/Talks/04_session_1_summary.html)
- (10.10 - 10.30) Coffee Break
- (10.30 - 11.00) [Exercise: Hello Keras (Classification)](Exercises/03_hello_keras.md)
- (11.00 - 11.15) [Brief talk: A bit more on Keras](http://htmlpreview.github.io/?https://github.com/leonjessen/RPharma2019/blob/master/Talks/05_a_bit_more_on_keras.html)
- (11.15 - 11.45) [Exercise: Predicting Price (regression)](Exercises/04_diamonds_regression.md)
- (11.45 - 12.15) [Exercise: Deep Learning for Cancer Immunotherapy](Exercises/05_deep_learning_for_cancer_immunotherapy.md)
- (12.15 - 12.30) [Brief talk: Session 2 Summary and Q&A](http://htmlpreview.github.io/?https://github.com/leonjessen/RPharma2019/blob/master/Talks/06_session_2_summary.html)
## Additional Resources
### Web
* [R Interface to TensorFlow](https://tensorflow.rstudio.com/)
* [R interface to Keras](https://tensorflow.rstudio.com/keras/)
* [Keras Examples](https://tensorflow.rstudio.com/keras/articles/examples/)
* [Invited Blog Posts](https://blogs.rstudio.com/tensorflow/)
* [Learning Resources](https://tensorflow.rstudio.com/learn/resources.html)
* [RStudio Community](https://community.rstudio.com/)
* [RStudio Cloud](https://rstudio.cloud/)
* [Deep Learning with Keras Cheatsheet](https://github.com/rstudio/cheatsheets/raw/master/keras.pdf)
### Books
* [Deep Learning with R](https://www.manning.com/books/deep-learning-with-r)
* [Free: Deep Learning book](https://www.deeplearningbook.org/)
* [Free: R for Data Science by Garrett Grolemund and Hadley Wickham](https://r4ds.had.co.nz/)
* [Free: ModernDive - An Introduction to Statistical and Data Sciences via R](https://moderndive.com/)