Deep Learning: Understanding "Attention is all you need" (2017)

Join us for an insightful discussion on the groundbreaking paper "Attention is all you need" (2017) by Vaswani et al. [link], which revolutionized the field of natural language processing and machine translation. This meetup aims to delve deep into the concepts introduced in the paper and explore their implications for modern deep learning architectures.

Agenda:
We'll meet around 18:30 and chat a bit around a bit of food/snacks and drinks. So please come early if you can. Then we'll move to the main part, which might look like that:

• Introduction to the Paper: A brief overview of the key ideas presented in "Attention is all you need".
• Discussion and Analysis: An in-depth exploration of the attention mechanism and its significance in neural network architectures.
• Q&A Session: An opportunity for participants to ask questions, share insights, and engage in discussions.

Who should Attend:
Attendees are expected to have read the paper (or at least given an attempt to read it). If you prefer videos or books, we have listed a few sources that discuss the transformer architecture in video or book form. See the resources section below.

In case you have questions or thoughts about the Attention mechanism or the Transformer architecture, please bring them to the event. We will use that as a basis for our discussion.

Helpful resources:

• The paper itself [link]
• For those who like it visual without math-formulas: "Depp Learning a visual approach" by Andrew Glassner [link]
• Programming course by Karpathy teaching deep learning and neural networks from the ground up [link]
• you'll find plenty more on google or youtube

For further details, please contact the event organizers (see above).
We look forward to seeing you there!