What we’re about
Work through classes and projects at your own pace at home. Come to a study session to ask and answer questions, then present what you've learned.
All experience levels and professional backgrounds are welcome!
If you're not sure where to start try:
- Deep Learning Fundamentals with Sebastian Raschka
- or Andrew Ng's Deep Learning Specialization on Coursera
- Practical Deep Learning for Coders and From Deep Learning Foundations to Stable Diffusion from fast.ai
- Feel-good videos from 3Blue1Brown
So, you've played with the chatty models:
- Now try Neural Networks: Zero to Hero with Andrej Karpathy to build and train a transformer as good as GPT-2 from scratch in Python
- Or Langchain & Vector Databases in Production
- Then go Beyond Jupyter notebooks
Go all in with these free textbooks:
- Understanding Deep Learning by Simon Prince
- Deep Learning: Foundations and Concepts by Chris Bishop
- Mathematics for Machine Learning by Marc Peter Diesenroth
- Introduction to Statistical Learning with R or Python
-----------------------------------------------------------------------------------------------------------------------------------------------------
Disclaimer & Code of Conduct:
Deep Learning RTP Meetup is a fully open-source, public forum. No expectation of privacy or secrecy regarding content or discussion either in person, in writing, or electronically should be assumed. Please refrain from including or sharing confidential material including, but not limited to, proprietary content, trade secrets, and classified and sensitive material.
Deep Learning Meetup is not liable for the content and/or discussion presented or shared in any form by individual members, visitors, or speakers. This disclaimer extends to all forms of Deep Learning Meetup’s events, discussion, and media- including, but not limited to, chat clients, digital workspaces and storage, and group discussions or collaborative projects.
DL RTP really likes the Recurse Center Rules. If a participant engages in harassing behavior, the organizers may take any action they deem appropriate, including warning the offender or expelling them from the class/event/meetup group.
Feel free to contact any of the DL Meetup Co-organizers with feedback or questions. Thank you for helping to ensure a healthy and friendly environment for all!
---------------------------------------------------------------------------------------------------------------
Weekly sessions:
Wednesdays: noon - 2 pm @ The Frontier RTP
Monthly sessions:
4th Tuesdays: 6-8 pm @ Downtown Durham
-----------------------------------------------------------------------------------------------------------------------------------------
**Need to refresh the following links from 2019 and before**
What you need to get started in Deep Learning
Here's a link to Study Material.
Recent history of deep learning from the fantastic podcast Talking Machines:
> • History of Deep Learning from the Inside Out - Part 1 and Part 2
Resources we've used in this study group:
> • Start with Practical Deep Learning for Coders from fast.ai
> • Networks and Deep Learning from Michael Nielsen
> • Machine Learning for Artists by Gene Kogan et al
> • Machine Learning with Scikit-Learn & Tensorflow by Aurelien Geron
Courses worth looking into:
> • Deep Natural Language Processing from Oxford
> • Convolutional Neural Networks for Visual Image Recognition from Stanford
> • Numerical Linear Algebra from fast.ai
To Infinity and Beyond:
As the number of deep learning tutorials and lists of lists approaches infinity, here are some places to browse -
> • and Arxiv Sanity Preserver
Upcoming events (1)
See all- Neural Network Coding WorkshopDurham County Main Library, Durham, NC
Join us for our monthly hands-on coding workshop.
We're working through Andrej Karpathy's "Neural Networks: Zero to Hero" series to build a transformer architecture and reproduce GPT-2.
"We start with the basics of backpropagation and build up to modern deep neural networks, like GPT. Language models are an excellent place to learn deep learning, even if you intend to eventually go to other areas like computer vision. Most of what you learn will be immediately transferable."
This Month's Focus
First, we'll review the first two projects in the series:- micrograd: A tiny autograd engine to implement backpropagation.
- makemore: An introduction to auto-regressive language modeling starting with a character-level approach, then adding an MLP and building up to a transformer.
Then introduce the final project, nanoGPT, which ties things together in one package.
Finally, we'll check in on EurekaLabs to see if there is any more code for LLM101n -- the next level of this course
Preparation
Before the workshop, please:- Watch the first six lessons of the "Neural Networks: Zero to Hero" series.
- Try to code up "micrograd" and "makemore" independently.
Prerequisites
- Solid programming skills in Python
Everyone is welcome!
Don't hesitate to reach out if you have any questions.
