This repository contains the materials for D-Lab Python Deep Learning workshop.

We recommend attending Python Fundamentals prior to this workshop. Python Machine Learning is also recommended as a supplemental course.

Check out D-Lab’s Workshop Catalog to browse all workshops, see what’s running now, and review prerequisites.

In this workshop, our goals are to recognize the architecture of a vanilla neural network, create our own network, and improve its performance using various standard techniques. We will use Keras (Python) for this workshop.

After this workshop, you will be able to:

• Recognize the architecture of a vanilla neural network
• Explain how forward and backward propagation contribute to model learning
• Create and evaluate the accuracy of a vanilla neural network
• Design new model architectures to improve performance

This workshop does not cover the following:

• CNNs or RNNs. Please let us know if these are of interest for a future workshop.
• Transformers. An exploratory workshop in LLMs is offered in LLMs Exploratory Research.

We will use Python to go through the workshop materials, we recommend using through the conda or miniconda distribution. Complete the following steps:

1. Follow the steps to download miniconda here.
2. Download these workshop materials:
   • Click the green "Code" button in the top right of the repository information.
   • Click "Download Zip".
   • Extract this file to a folder on your computer where you can easily access it (we recommend Desktop).
3. Optional: if you’re familiar with git, you can instead clone this repository by opening a terminal and entering [GitCloneCommand].

If you do not have Python installed and the materials loaded on your workshop by the time it starts, we strongly recommend using the UC Berkeley Datahub to run the materials for these lessons. You can access the DataHub by clicking the following button:

The DataHub downloads this repository, along with any necessary packages, and allows you to run the materials in an RStudio instance on UC Berkeley's servers. No installation is necessary from your end - you only need an internet browser and a CalNet ID to log in. By using the DataHub, you can save your work and come back to it at any time. When you want to return to your saved work, just go straight to the D-Lab DataHub, sign in, and you click on the [Workshop-Name] folder.

If you don't have a Berkeley CalNet ID, you can still run these lessons in the cloud, by clicking this button:

By using this button, however, you cannot save your work.

Now that you have all the required software and materials, you need to run the code:

Provide instructions on running the code, including how to load relevant software (RStudio, Jupyter Notebooks, etc.) and which file to open up. See other repositories for examples.

Additionally, provide instructions on how to run code once it’s open (running Jupyter cells, RMarkdown cells, etc.).

Check out the following resources to learn more about deep learning from a language-agnostic viewpoint:

• Dive into Deep Learning: This textbook provides a comprehensive introduction to deep learning, from the basic necessary math (calculus, linear algebra) to vanilla neural nets, CNNs, RNNs, transformers, LLMs, hyperparameter tuning, optimization, and more. Highly recommended.

D-Lab works with Berkeley faculty, research staff, and students to advance data-intensive social science and humanities research. Our goal at D-Lab is to provide practical training, staff support, resources, and space to enable you to use R for your own research applications. Our services cater to all skill levels and no programming, statistical, or computer science backgrounds are necessary. We offer these services in the form of workshops, one-to-one consulting, and working groups that cover a variety of research topics, digital tools, and programming languages.

Visit the D-Lab homepage to learn more about us. You can view our calendar for upcoming events, learn about how to utilize our consulting and data services, and check out upcoming workshops.

Here are other Python workshops offered by the D-Lab:

Python Fundamentals

Python Machine Learning Python GPT Fundamentals Python Web Scraping

• Anna Björklund
• Sean Perez (legacy)
• Pratik Sachdeva (legacy)