Neural Networks and Deep Learning - Part II (Practice)

Software

• High-level software focuses on user-friendly interface to specify and train models.
  Keras, PyTorch (only Linux and MacOS), scikit-learn, …

• Lower-level software focuses on developer tools for impelementing deep learning models.
  TensorFlow, Theano, CNTK, Caffe, Torch, …

• Most tools are developed in Python plus a low-level language.

TensorFlow

• Developed by Google Brain team for internal Google use. Formerly DistBelief.

• Open sourced in Nov 2015.

• OS: Linux, MacOS, and Windows (since Nov 2016).

• GPU support: NVIDIA CUDA.

• TPU (tensor processing unit), built specifically for machine learning and tailored for TensorFlow.

• Mobile device deployment: TensorFlow Lite (May 2017) for Android and iOS.

• Used in a variety of Google apps: speech recognition (Google assistant), Gmail (Smart Reply), search, translate, self-driving car …

when you have a hammer, everything looks like a nail.

• Machine Learning Crash Course (MLCC). A 15 hour workshop available to public since March 1, 2018.

R/RStudio

R users can access Keras and TensorFlow via the keras and tensorflow packages.

#install.packages("keras")
library(keras)
install_keras()
# install_keras(tensorflow = "gpu") # if NVIDIA GPU is available

Example: MNIST - MLP

Rmd, html.

Example: MNIST - CNN

Rmd, html.

Example: Generate text from Nietzsche’s writings - RNN LSTM

Rmd, html.

Example: IMDB review sentiment analysis - RNN LSTM

Rmd, html.

Example: Generate handwritten digits from MNIST - GAN

Rmd, html.