Deep Learning using Keras with Tensorflow backend in R

class: sf-title-slide 
<a href="https://github.com/rstudio-conf-2020/dl-keras-tf"><img style="position: absolute; top: 0; right: 0; border: 0;" src="https://s3.amazonaws.com/github/ribbons/forkme_right_darkblue_121621.png" alt="Fork me on GitHub"></a>

# .font250.white[Deep Learning with ]
## .font120.white[Using Keras with Tensorflow backend]

.white[Brad Boehmke]  
.white[rstudio::conf(2020)]  
.white[rstd.io/conf20-dl]

---
# Workshop policies

.pull-left[

]

.pull-right.font90[

* Identify the exits closest to you in case of emergency

* Please review the rstudio::conf code of conduct that applies to all workshops. Issues can be addressed three ways:
   - In person: contact any rstudio::conf staff member or the conference registration desk
   - By email: send a message to conf@rstudio.com
   - By phone: call 844-448-1212

* Please do not photograph people wearing red lanyards

* A chill-out room is available for neurologically diverse attendees on the 4th floor of tower 1

]

---

# About me <img src="images/about_me_bitmoji.png" height="60" width="60", align="right">

.pull-left[

]

.pull-right[

]

---
# About me <img src="images/about_me_bitmoji.png" height="60" width="60", align="right">

.pull-left[

]

.pull-right[

]

---
# About me <img src="images/about_me_bitmoji.png" height="60" width="60", align="right">

.pull-left[

]

.pull-right[

]

---
# About me <img src="images/about_me_bitmoji.png" height="60" width="60", align="right">

.pull-left[

]

.pull-right[

]

---

# About me <img src="images/about_me_bitmoji.png" height="60" width="60", align="right">

.pull-left[

]

.font120.pull-right[
 
[<svg style="height:0.8em;top:.04em;position:relative;fill:steelblue;" viewBox="0 0 496 512"><path d="M336.5 160C322 70.7 287.8 8 248 8s-74 62.7-88.5 152h177zM152 256c0 22.2 1.2 43.5 3.3 64h185.3c2.1-20.5 3.3-41.8 3.3-64s-1.2-43.5-3.3-64H155.3c-2.1 20.5-3.3 41.8-3.3 64zm324.7-96c-28.6-67.9-86.5-120.4-158-141.6 24.4 33.8 41.2 84.7 50 141.6h108zM177.2 18.4C105.8 39.6 47.8 92.1 19.3 160h108c8.7-56.9 25.5-107.8 49.9-141.6zM487.4 192H372.7c2.1 21 3.3 42.5 3.3 64s-1.2 43-3.3 64h114.6c5.5-20.5 8.6-41.8 8.6-64s-3.1-43.5-8.5-64zM120 256c0-21.5 1.2-43 3.3-64H8.6C3.2 212.5 0 233.8 0 256s3.2 43.5 8.6 64h114.6c-2-21-3.2-42.5-3.2-64zm39.5 96c14.5 89.3 48.7 152 88.5 152s74-62.7 88.5-152h-177zm159.3 141.6c71.4-21.2 129.4-73.7 158-141.6h-108c-8.8 56.9-25.6 107.8-50 141.6zM19.3 352c28.6 67.9 86.5 120.4 158 141.6-24.4-33.8-41.2-84.7-50-141.6h-108z"/></svg>](http://bradleyboehmke.github.io/) bradleyboehmke.github.io 
[<svg style="height:0.8em;top:.04em;position:relative;fill:steelblue;" viewBox="0 0 496 512"><path d="M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6zm-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3zm44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9zM244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8zM97.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1zm-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7zm32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1zm-11.4-14.7c-1.6 1-1.6 3.6 0 5.9 1.6 2.3 4.3 3.3 5.6 2.3 1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2z"/></svg>](https://github.com/bradleyboehmke/) @bradleyboehmke 
[<svg style="height:0.8em;top:.04em;position:relative;fill:steelblue;" viewBox="0 0 512 512"><path d="M459.37 151.716c.325 4.548.325 9.097.325 13.645 0 138.72-105.583 298.558-298.558 298.558-59.452 0-114.68-17.219-161.137-47.106 8.447.974 16.568 1.299 25.34 1.299 49.055 0 94.213-16.568 130.274-44.832-46.132-.975-84.792-31.188-98.112-72.772 6.498.974 12.995 1.624 19.818 1.624 9.421 0 18.843-1.3 27.614-3.573-48.081-9.747-84.143-51.98-84.143-102.985v-1.299c13.969 7.797 30.214 12.67 47.431 13.319-28.264-18.843-46.781-51.005-46.781-87.391 0-19.492 5.197-37.36 14.294-52.954 51.655 63.675 129.3 105.258 216.365 109.807-1.624-7.797-2.599-15.918-2.599-24.04 0-57.828 46.782-104.934 104.934-104.934 30.213 0 57.502 12.67 76.67 33.137 23.715-4.548 46.456-13.32 66.599-25.34-7.798 24.366-24.366 44.833-46.132 57.827 21.117-2.273 41.584-8.122 60.426-16.243-14.292 20.791-32.161 39.308-52.628 54.253z"/></svg>](https://twitter.com/bradleyboehmke) @bradleyboehmke 
[<svg style="height:0.8em;top:.04em;position:relative;fill:steelblue;" viewBox="0 0 512 512"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>](mailto:bradleyboehmke@gmail.com) bradleyboehmke@gmail.com

]

---
class: inverse, center, middle

# What are we going to cover?

---
# Modeling purposes

.font130[
.pull-left[
* Regression

* Classification

* Computer vision

* Recommendation systems

* Natural language processing
]
]

---
# Model architectures

.font130[
.pull-left.opacity20[
* Regression

* Classification

* Computer vision

* Recommendation systems

* Natural language processing
]

.pull-right[
* Multilayer perceptron (MLP)

* Convolutional neural networks (CNNs)

* Transfer learning

* Recurrent neural networks (RNNs)

* Long-short term memory neural networks (LSTMs)
]
]

---
# Model gears

.font130[

.pull-left[
* Tensors

* Sequential vs functional models

* Activation functions

* Derivatives & gradient descent

* Backward propagation

* Batches & epochs

]

.pull-right[

* Learning rate

* Convolutions

* Embeddings

* Recurrent connections

* and more!

]

---
# Workflow procedures

.font130[

.pull-left[
* Data preprocessing

* Data augmentation

* Network architecture

* Model compiling

* Regularization

* Hyperparameter tuning

]

.pull-right[
* Callbacks procedures

* Model validation

* Transfer learning

* Model interpretation

* and more!

]
]

---
class: inverse

# My objective is to...

.font130.white[

* Provide an intuitive understanding of the engines and architectures that drive deep learning.

* Apply a variety of deep learning algorithms.

* Establish a mental model of deep learning.
]

---
# I assume you are...

.font130[New to the field of deep learning and neural networks but eager to learn.]

.font130[An experienced R user comfortable with both tidyverse & non-tidyverse code, creating functions, and applying control (i.e. if, ifelse) and iteration (i.e. for, while) statements.]

.font130[Familiar with machine learning concepts such as data splitting, feature engineering, resampling procedures (i.e. k-fold cross validation), hyperparameter tuning, and model validation.]

---
class: inverse, center, middle

# How are we going to learn?

---
# Hands-on notebooks

.pull-left[

.center[Active learning]

]

.pull-right[

https://github.com/rstudio-conf-2020/dl-keras-tf

]

---
# Course overview

.font90[

.pull-left[

.center[.bold[Day 1]]

| Time          | Activity                  |
| :------------ | :------------------------ |
| 09:00 - 09:30 | Introduction              |
| 09:30 - 10:30 | Deep learning ingredients |
| 10:30 - 11:00 | *Coffee break*            |
| 11:00 - 12:30 | Deep learning recipe      |
| 12:30 - 13:30 | *Lunch break*             |
| 13:30 - 15:00 | Computer vision & CNNs    |
| 15:00 - 15:30 | *Coffee break*            |
| 15:30 - 17:00 | Project                   |

]
]

.font90[

.pull-right[

.center[.bold[Day 2]]
 
| Time          | Activity                  |
| :------------ | :------------------------ |
| 09:00 - 10:30 | Word embeddings           |
| 10:30 - 11:00 | *Coffee break*            |
| 11:00 - 12:30 | Collaborative filtering   |
| 12:30 - 13:30 | *Lunch break*             |
| 13:30 - 15:00 | RNNs & LSTMs              |
| 15:00 - 15:30 | *Coffee break*            |
| 15:30 - 17:00 | Final project & wrap up   |

]
]

---
# That's a lot of material!

.pull-left[

### You may be overwhelmed

]

.pull-right[

### So work together

]

---
class: yourturn
# Your Turn!

## .font140[Meet your neighbors:]

.font130[
1. What is their experience with R, machine learning, and/or deep learning?

2. What programming experience other than R do they have?

3. How are they using, or how do they plan to use, R and deep learning in their job?
]

---
class: yourturn
# Your Turn!

## .font140[Meet your neighbors:]

---
# Meet your friendly TAs

.pull-left[

.center[[Rick Scavetta](https://github.com/Scavetta)]
<img src="images/rick_scavetta.jpeg" width="40%" height="40%" style="display: block; margin: auto;" />

.center[[Doug Ashton](https://github.com/dougmet)]
<img src="https://avatars3.githubusercontent.com/u/5878305?s=460&v=4" width="40%" height="40%" style="display: block; margin: auto;" />

]

.pull-right[

.center[[Omayma Said](https://www.onceupondata.com/)]
<img src="images/omayma_said.jpg" width="40%" height="40%" style="display: block; margin: auto;" />

.center[[Daniel Rodriguez](https://github.com/danielfrg)]
<img src="https://avatars3.githubusercontent.com/u/1580714?s=460&v=4" width="40%" height="40%" style="display: block; margin: auto;" />

]

---
# Asking Questions

.pull-left[

.center.font140[Deep learning]

]

.pull-right[

.center.font140[Code, server, logistics, admin]

]

---
class: inverse, center, middle

# Why deep learning?

---
class: clear, center, middle
background-image: url(images/01-ai-ml-dl-landscape.002.jpeg)
background-size: cover

---
# Why deep learning?

.font140.pull-left[

* .font120[Automated feature extraction]

]

.pull-right[

]

.footnote[Image: [Sambit Mahapatra](https://towardsdatascience.com/why-deep-learning-is-needed-over-traditional-machine-learning-1b6a99177063)]

---
# Why deep learning?

.font140.pull-left[

* Automated feature extraction

* Problem solving flexibility

]

.pull-right[
 
<img src="images/prob-solve-flex.png" width="315" style="display: block; margin: auto;" />

]

---
# Why deep learning?

.font140.pull-left[

* Automated feature extraction

* Problem solving flexibility

* Scales efficiently 🧐
]

.pull-right[

]

.footnote[Image: [Andrew Ng](https://www.deeplearning.ai/content/uploads/2018/09/Ng-MLY01-12.pdf)]

---
class: inverse, center, middle

# Why Keras?

---
# Deep learning frameworks

---
# Deep learning frameworks

---
# My preferred DL framework

---
# On the shoulders of giants

.pull-left[

.center[Francois Chollet]
<img src="images/francois_challet.jpeg" width="40%" height="40%" style="display: block; margin: auto;" />

.center[J.J. Allaire]
<img src="images/jjallaire.jpg" width="40%" height="40%" style="display: block; margin: auto;" />

]

.pull-right[

]

---
class: inverse, center, middle

# Ready?

.center.white[_Let’s start get started!_]

---
# Back home

[.center[]](https://github.com/rstudio-conf-2020/dl-keras-tf)

.center[https://github.com/rstudio-conf-2020/dl-keras-tf]