Lecture notes, readings, code samples and resources for teaching yourself how PyTorch and Tensorflow.
This class was formerly taught as a bootcamp but is now a self-paced online resource.
See Brad's GitHub Stars for a curated collection of helpful resources.
Session | Topic | TODO |
---|---|---|
Preparation | N/A | See preparation.md |
π Week 1 | π Roles, Machine Learning Basics, Tech Stack | How Deep Learning Works and Intro to Free Software |
π Week 1 | π¬ "Foundations" Live Demos | SuperDataScience Code Interpreter Guide |
π Week 2 | π‘ Final Project Ideas | Pick a project! |
π Week 2 | π The Universal ML Workflow | The Universal ML Workflow and The Regression Theory of Everything |
π Week 3 | π₯ Pair Programming, Project Q&A | work on your project |
π Week 3 | π Data Engineering, ETL Basics and Data Wrangling Techniques | work on your project |
π Week 4 | π OpenRouter Sommelier App in AWS, Azure and GCP Cloud Setup Demo | Setup AWS Free Tier |
π Week 5 | π§ Metrics and Loss Functions, Model Architecture and Hyperparameters | 60 Minute Pytorch Blitz |
π Week 7 | π After The Bootcamp... | go forth and win! |
π Weeks 7-8 | π Project Presentations | brag about yourself online |
Participants will dedicate substantial time to final projects aligned with their β¨career aspirationsβ¨. For an array of past presentations and source code, πΊ visit Brad's Youtube Channel.
Step | Details |
---|---|
Generate synthetic text data using Scikit-LLM. Explore datasets on Kaggle or Hugging Face. | |
Beginner: Follow TensorFlow quickstart for basic image/text classifiers. Recommended: Dive into 60 Minute PyTorch Blitz, then explore π PyTorch Text Classification or PyTorch Image Classification. More Advanced: Fine-tune pretrained models with Hugging Face for π text or πΈ image classification. Apple Nerds Only Use MLX. | |
β Challenge and Experiment (Optional) | Advanced: Explore cross-platform frameworks like Keras Core. π Very Advanced: Attempt to Replicate a Winning Model from Kaggle. |