Deep Learning RTP

Deep Learning RTP is a study group for people who want to understand and build neural networks. Each weekly session is a paper review or a technical deep dive. Between sessions, work through a course or project at your own pace; then come to ask questions, answer them, or present what you've figured out.

All experience levels and professional backgrounds are welcome.

We meet Wednesdays at lunchtime at The Frontier in RTP, hybrid in-person and over Zoom (link sent when you RSVP).

Not sure where to start? Pick a track below and dive in.
New here - start with the basics

• The wonderful Neural Networks series from 3Blue1Brown now includes chapters on LLMs and transformers too

• MIT 6.S191: Introduction to Deep Learning — MIT's intro, fully open-sourced (lectures, slides, and labs)

• The classic (2022) Practical Deep Learning for Coders and Part 2: From Foundations to Stable Diffusion from fast.ai

  The chatty models are everywhere - build on from scratch

• The Illustrated Transformer by Jay Alammar peruse before you write any code

• Introduction to Modern AI (10-202) — CMU's Zico Kolter takes you from linear models to a working LLM chatbot, including post-training, RLHF, and reasoning. (PyTorch, Colab/Marimo)

• Neural Networks: Zero to Hero — Andrej Karpathy walks you from backprop to a GPT-2-class transformer, in plain Python

• Build a Large Language Model (From Scratch) — Sebastian Raschka's book with a runnable code repo: tokenizer, attention, pretraining, and finetuning, all in PyTorch on a laptop

  Free textbooks

• Understanding Deep Learning by Simon Prince

• Deep Learning: Foundations and Concepts by Chris Bishop & Hugh Bishop — free digital edition

• Probabilistic Machine Learning by Kevin Murphy — two free volumes (Introduction and Advanced Topics); the most comprehensive modern probabilistic reference

• Dive into Deep Learning by Zhang, Lipton, Li & Smola — interactive book with runnable code in PyTorch, JAX, and TensorFlow

• Mathematics for Machine Learning by Deisenroth, Faisal & Ong

• An Introduction to Statistical Learning, with Python or R

  Courses and references worth a look

• Stanford CS336: Language Modeling from Scratch — the deep, systems-level version of building an LLM end to end (tokenizers, GPUs, parallelism, scaling laws); 2025 lectures and materials are free online

• Classics: Stanford CS231n (computer vision) and CS224n (NLP)

• Neural Networks and Deep Learning by Michael Nielsen — a concise classic

• Computational Linear Algebra from fast.ai

• Awesome Deep Learning — a maintained meta-list when you want to browse further

  Sessions

• Weekly: Wednesdays, noon–2pm @ The Frontier, RTP — paper reviews and technical deep dives, hybrid (Zoom link on RSVP)

• Evening social — "Humans in The Loop": [cadence and venue TBA]

***

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!