ETH Google Developer Student Group - Workshops on Neural Networks

This repositories contains the material for 4 workshops given at the ETH together with the Google Developer Student Group.

Registration Link: REGISTER HERE

Online Material

A lot of material on Deep Learning and nueral network can be found at my book companion website. My book (Applied Deep Learning with TensorFlow 2 published by Springer/APRESS) can be bought here.

Lecture 1 - 21st April 2022 - Introduction to Keras and Neural Networks

In this lecture we will look first at Jupyter notebooks. Those are the common tool used by data scientists and machine learning engineering during the exploratory phase of the machine learning pipeline. We will look at Google Colab, an online version of Jupyter notebooks that does not require any local installation. We will use this tool during our lectures. After that we will look at TensorFlow and Keras and how they work. We will look at very basic examples and then at advanced usage. Finally we will have a hands-on session in which we will use Keras to build a very easy neural network to classify images.

Link to the lecture material

1. Google colab - An Introduction
2. Keras and TensorFlow - An Introduction PowerPoint Download Link
3. Introduction to Neural Networks PowerPoint Download Link
4. Multi-Task Learning with Keras PowerPoint Download Link
5. Hands-on session - Easy Network with Keras
6. Hands-on session - Custom Training loop basic Example
7. Hands-on session - Convolutional Neural Network and classification

Additional and Bonus Material

• A nice video introduction to Google Colab can be found in this video. The official website for the jupyter notebook project can be found here.

• You can also find an introduction to Neural Networks in the slides for a lecture given by Umberto Michelucci at the ETH university in Zürich, Switzerland. They are google slides and should be accessible online easily.

  Lecture on Neural Networks

• Here you can find lots of material on Convolutional Neural Networks from a 2-day workshop I gave in London at the O'Reilly conference Link to GitHub

Lecture 2 - Autoencoders

In this lecture we will look at autoencoders. You can find an introduction in this paper I wrote

Introduction to Autoencoders by Michelucci

that can be found also on arxiv (Michelucci, Umberto. "An Introduction to Autoencoders." arXiv preprint arXiv:2201.03898 (2022))

Link to Jupyter notebooks

1. Hands-on session: Your first autoencoder
2. Hands-on session: Anomaly Detection with Autoencoders
3. Hands-on session: Denoising Images with FFA
4. Hands-on session: Denoising Images with CNN