/AI-101

Notes, links and code samples and resources for teaching yourself pytorch and tensorflow.

Primary LanguageJupyter NotebookGNU General Public License v3.0GPL-3.0

AI-101 πŸš€

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.

More Like This ⭐

See Brad's GitHub Stars for a curated collection of helpful resources.

Course Outline πŸ“

Session Topic TODO
Preparation N/A See preparation.md
πŸ“… Week 1 πŸ“š Roles, Machine Learning Basics, Tech Stack How Deep Learning Works and Intro to Free Software
πŸ“… Week 1 🎬 "Foundations" Live Demos SuperDataScience Code Interpreter Guide
πŸ“… Week 2 πŸ’‘ Final Project Ideas Pick a project!
πŸ“… Week 2 πŸ“Š The Universal ML Workflow The Universal ML Workflow and The Regression Theory of Everything
πŸ“… Week 3 πŸ‘₯ Pair Programming, Project Q&A work on your project
πŸ“… Week 3 πŸ“ Data Engineering, ETL Basics and Data Wrangling Techniques work on your project
πŸ“… Week 4 πŸ“Š OpenRouter Sommelier App in AWS, Azure and GCP Cloud Setup Demo Setup AWS Free Tier
πŸ“… Week 5 🧠 Metrics and Loss Functions, Model Architecture and Hyperparameters 60 Minute Pytorch Blitz
πŸ“… Week 7 πŸŽ“ After The Bootcamp... go forth and win!
πŸ“… Weeks 7-8 πŸŽ‰ Project Presentations brag about yourself online

πŸš€ Final Project Sequence πŸš€

Participants will dedicate substantial time to final projects aligned with their ✨career aspirations✨. For an array of past presentations and source code, πŸ“Ί visit Brad's Youtube Channel.

Step Details
πŸ…°οΈ Data Collection and Simple Model Generate synthetic text data using Scikit-LLM. Explore datasets on Kaggle or Hugging Face.
πŸ…±οΈ Custom Model (Optional) Beginner: Follow TensorFlow quickstart for basic image/text classifiers. Recommended: Dive into 60 Minute PyTorch Blitz, then explore πŸ“œ PyTorch Text Classification or PyTorch Image Classification. More Advanced: Fine-tune pretrained models with Hugging Face for πŸ“ text or πŸ“Έ image classification. Apple Nerds Only Use MLX.
⭐ Challenge and Experiment (Optional) Advanced: Explore cross-platform frameworks like Keras Core. πŸ† Very Advanced: Attempt to Replicate a Winning Model from Kaggle.