Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/toelt-llc/course-supsi-lectures-2024


https://github.com/toelt-llc/course-supsi-lectures-2024

Last synced: about 7 hours ago
JSON representation

Awesome Lists containing this project

README 

        
# SUPSI Lectures - Spring 2024

This repositories contains the material for 2 lectures given at the Italian university of applied science in Switzerland.



# Online Material



A lot of material on Deep Learning and nueral network can be found at my [book companion website](https://adl.toelt.ai). My book (Applied Deep Learning with TensorFlow 2 published by Springer/APRESS) can be [bought here](https://link.springer.com/book/10.1007/978-1-4842-8020-1).



# Lecture 1 - 8th April 2024 - Introduction to Neural Networks, Keras and Jupyter Notebooks



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 leaving advanced usage to further study. Finally we will have a hands-on session in which we will use Keras to build a very easy neural network to classify images.



## Lecture material



1. [Google colab](https://colab.research.google.com/notebooks/welcome.ipynb#recent=true) - An Introduction

2. Keras and TensorFlow - An Introduction (Folder 1)

3. Hands-on session (Folder 1)



## Additional and Bonus Material



- A nice video introduction to Google Colab can be found in [this video](https://www.youtube.com/watch?v=HW29067qVWk&t=212s). The official website for the jupyter notebook project can be found [here](https://jupyter.org). 



- 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](https://docs.google.com/presentation/d/1SbPDwVeBwG4FoV1ySLGyc6C2C8r0vcKgEF4v8IvaSlE/edit?usp=sharing)



# Lecture 2 - 16th April 2024 - Introduction to Autoencoders



In this lecture we will look at what autoencoders are and what you can do with those special neural network architecture. A complete introduction can be found in [this paper](https://arxiv.org/abs/2201.03898). We will look at the following topics



- What are autoencoders ([Introduction Paper](https://arxiv.org/abs/2201.03898))

- Denoising autoencoders

- Autoencoders for dimensionality reduction



## Code examples



- [Your first autoencoder](https://colab.research.google.com/github/toelt-llc/ADL-Book-2nd-Ed/blob/master/docs/Autoencoders/Your_first_autoencoder_with_Keras.ipynb)

- [Anomaly Detection with autoencoders](https://colab.research.google.com/github/toelt-llc/ADL-Book-2nd-Ed/blob/master/docs/Autoencoders/Anomaly_detection_with_autoencoders.ipynb)

- [Denoising Autoencoders with Feed Forward Neural Networks](https://colab.research.google.com/github/toelt-llc/ADL-Book-2nd-Ed/blob/master/docs/Autoencoders/Denoising_autoencoders_with_FFNN.ipynb)

- [Denoising Autoencoders with Convolutional Neural Networks](https://colab.research.google.com/github/toelt-llc/ADL-Book-2nd-Ed/blob/master/docs/Autoencoders/Denoising_autoencoders_with_CNN.ipynb)