Neural Networks in a Nutshell

Installation Notes

This tutorial requires *jupyter, tensorflow and keras. These can be installed with pip by typing the following in Terminal:

pip install jupyterlab tensorflow keras pandas sklearn

We will be reviewing the materials with Jupyter notebooks. You should be able to type

jupyter-lab

in your terminal window and see the notebook panel load in your web browser.

Presentation Format

This tutorial is designed to get the audience training neural networks at the end of a 1-hour session. In particular, it covers areas where neural networks really shines - CNNs and RNNs. These techniques are applied on the Kaggle Titanic, MNIST and Rotten Tomatoes datasets.

• Section 1-0 - Prelude
• Section 1-1 - Basic NN, Titanic
• Section 2-1 - Basic NN, MNIST
• Section 2-2 - Regularized NN
• Section 2-3 - CNN
• Section 3-3 - RNN
• Appendix - SGD