Deep Learning in R - part I

With the release of the R Keras package (https://keras.rstudio.com/) (by JJ Allaire and Francois Chollet) at the end of 2017 / beginning 2018 the topic of artificial neural networks and especially deep learning in R became red-hot within the R community.

„Deep Learning in R” will be a series of workshops during which you will learn how to use Keras/Tensorflow to solve different deep learning problems using Feedforward, Convolutional, and Recurrent Neural Networks. During workshops we will go through problems like image classification, object localization/detection, image segmentation, dimensionality reduction, time series forecasting, various NLP tasks and more. We will also talk about interpretability of Machine/Deep Learning models using LIME and DALEX packages.

In our first workshop we will introduce Keras and Tensorflow and we will show how to build Feedforward Neural Network.

After workshop we will have some pizza and drinks :)

Requirements:

Please make sure to bring your laptop including an up to date R version, RStudio and install `keras` package:

```

library(keras)

install_keras() # CPU version

# install_keras(tensorflow = "gpu") # GPU version (recommended)

```

For more info about Keras/Tensorflow installation go to: https://tensorflow.rstudio.com/reference/keras/install_keras/

Participants should know basics of Machine Learning like linear and logistic regression, MSE, Accuracy, Precision, Recall, overfitting etc. They should also know basics of programming in R.

During workshops unfortunately there will be no internet connection so participants have to download scripts and datasets before meeting: [LINK COMING SOON]