---
title: "Welcome"
author: "Prof. Eric A. Suess"
format: 
  revealjs:
    self-contained: true
---

## Welcome to Applied Deep Learning

We will be reading the **Deep Learning with R** book.

Or if you choose to use Python, you will be reading the **Deep Learning with Python** book.  You should also consider using the audio or video version of the book.

## RStudio tensorflow

RStudio has written an R package *tensorflow* to access tensorflow.

See the [RStudio tensorflow](https://tensorflow.rstudio.com).  

Here is the link to the [tensorflow](https://www.tensorflow.org) website.

## Playground 

Check out the [tensorflow playground](https://playground.tensorflow.org/) to experiment with neural networks.

Play with the different datasets and check to see how more nodes change the predictions and how more layers change the predictions.  Be sure to watch how the Loss gets smaller.

## Deep Learning is useful for

- image recognition
- time series forecasting
- language translation
- speech translation
- image generation
- text generation
- AI

## According to the author, about the book

In the Preface:

"radically democratize it"

"I wrote it with a focus on making the concepts behind deep learning, and their implementation, as approachable as possible. Doing so didn’t require me to dumb down anything—I strongly believe that there are no difficult ideas in deep learning. I hope you’ll find this book valuable and that it will enable you to begin building intelligent applications and solve the problems that matter to you."

## First look

- MNIST Problem

- See the Chapter 2 code.

## Tensors

- Scalars (0D tensors)
- Vectors (1D tensors)
- Matrices (2D tensors)
- 3D tensors and higher-dimensional tensors