Details
Last session we looked at the architecture of the Transformer and how it is used for NLP. This session we will continue looking at the Transformer and introduce the task of Computer Vision.
Here are a list of resources, of which we hope you will go through one or more of them so that you can bring what you have learnt to the meetup
General Transformer Architecture
Vision Transformer
We encourage you to spend some time with the material before the session. It is fine if you do not understand all of it. The purpose of this meetup is to ask questions and to learn.
If you would like to propose a research paper, blog post, Kaggle competition or something else as the topic for the following meeting, prepare a 30-60 second proposal. We will have these proposals at the end of the session.
We hope to see you there!
Meeting Schedule:
6:30 – Introductions
6:35 – Discussion
7:25 – Nominate and vote for following meeting’s next topic
7:30 – Meeting ends
Thanks to Thematic and GridAKL for sponsoring the group
For more information and registration: MeetUp