Online
Jul 5-7, 2021
9:00-13:00 CEST
Instructors: Berend Weel, Dafne van Kuppevelt, Florian Huber
Helpers: Sven van der Burg, Johan Hidding
Some adblockers block the registration window. If you do not see the registration box below, please check your adblocker settings.
This workshop gives an introduction to Deep Learning for researchers who are familiar with the basics of (non-deep) Machine Learning. We start with explaining the basic concepts of neural networks, and then we go through the different steps of a Deep Learning workflow. Participants will learn how to prepare data for deep learning, how to implement a basic Deep Learning model in Python with Keras, how to monitor and troubleshoot the training process and how to implement different layer types such as convolutional layers.
Who: This workshop is intended for researchers who are familiar with Python and the basics of Machine Learning.
Prerequired knowledge: Basic Python programming skills and familiarity with the Pandas package. Basic knowledge on Machine learning, including the following concepts: Data cleaning, train & test split, type of problems (regression, classification), overfitting & underfitting, metrics (accuracy, recall, etc.).
Where: This training will take place online. The instructors will provide you with the information you will need to connect to this meeting.
When: Jul 5-7, 2021. Add to your Google Calendar.
Requirements: Participants must have access to a computer with a Mac, Linux, or Windows operating system (not a tablet, Chromebook, etc.) that they have administrative privileges on. They should have a few specific software packages installed (listed below).
Accessibility: We are dedicated to providing a positive and accessible learning environment for all. Please notify the instructors in advance of the workshop if you require any accommodations or if there is anything we can do to make this workshop more accessible to you.
Contact: Please email training@esciencecenter.nl for more information.
Roles: To learn more about the roles at the workshop (who will be doing what), refer to our Workshop FAQ.
| 09:00 | Welcome and icebreaker |
| 09:15 | Introduction to Deep Learning |
| 10:15 | Break |
| 10:30 | Building a first model with Keras |
| 11:30 | Break |
| 11:45 | Building a first model with Keras |
| 12:45 | Wrap-up |
| 13:00 | END |
| 09:00 | Welcome and icebreaker |
| 09:15 | Recap |
| 09:45 | Monitoring and Troubleshooting the learning process |
| 10:30 | Break |
| 10:45 | Monitoring and Troubleshooting the learning process |
| 11:45 | Break |
| 12:00 | Monitoring and Troubleshooting the learning process |
| 12:45 | Wrap-up |
| 13:00 | END |
| 09:00 | Welcome and icebreaker |
| 09:15 | Recap |
| 09:45 | Convolutional neural networks |
| 10:30 | Break |
| 10:45 | Convolutional neural networks |
| 11:45 | Break |
| 12:00 | Regularization |
| 12:45 | Wrap-up and Post-workshop Survey |
| 13:00 | END |
To participate in a workshop, you will need access to the software described below. In addition, you will need an up-to-date web browser.
We maintain a list of common issues that occur during installation as a reference for instructors that may be useful on the Configuration Problems and Solutions wiki page.
If you haven't used Zoom before, go to the official website to download and install the Zoom client for your computer.
Like other Carpentries workshops, you will be learning by "coding along" with the Instructors. To do this, you will need to have both the window for the tool you will be learning about (a terminal, RStudio, your web browser, etc..) and the window for the Zoom video conference client open. In order to see both at once, we recommend using one of the following set up options:
Python is a popular language for research computing, and great for general-purpose programming as well. Installing all of its research packages individually can be a bit difficult, so we recommend Anaconda, an all-in-one installer.
Regardless of how you choose to install it, please make sure you install Python version 3.x (e.g., 3.6 is fine).
We will teach Python using the Jupyter Notebook, a programming environment that runs in a web browser (Jupyter Notebook will be installed by Anaconda). For this to work you will need a reasonably up-to-date browser. The current versions of the Chrome, Safari and Firefox browsers are all supported (some older browsers, including Internet Explorer version 9 and below, are not).
bash Anaconda3-and then press Tab to autocomplete the full file name. The name of file you just downloaded should appear.
yes and press enter to approve the license.
Press Enter (or Return)
to approve the default location
for the files.
Type yes and press
Enter (or Return)
to prepend Anaconda to your PATH
(this makes the Anaconda distribution the default Python).
You will need the following python packages for this workshop:
You can install these packages with conda or pip. If you installed Python with anaconda, as explained in the instructions on this page, you can install the packages with the conda package manager. Open an terminal and type:
conda install "tensorflow>=2.1" seaborn "scikit-learn>=0.22" pandas
You can download the data for this workshop using this link. More information on the dataset, including metadata, can be found here.
Make sure to download the data to a (new) directory where we will store all files for the workshop, including our notebooks with code.