The "craftsmanship" of machine learning, including principles and practical techniques of preparing data, designing training experiments, calibrating models, and choosing the right metrics for evaluation. Mastering the underlying algorithms for a wide range of ML tasks, including ML engineering techniques for building production-ready models.
Organized by AI Summer of Code (AISOC)
- Getting Started with Machine Learning (ML)
- Getting Started with Large Language Models (LLMs)
- Introduction to Machine Learning Algorithms
- Statistics Fundamentals for Machine Learning
- Preparing Data for Machine Learning
- ML Workflow with Python & Scikit-Learn
- Statistical Methods in Machine Learning I
- Introduction to Vector Embeddings
- Statistical Methods in Machine Learning II
- Mathematical Methods in Machine Learning I
- Neural Networks and Deep Learning
- Understanding LLM Architectures
- Embeddings & Vector Databases
- Mathematical Methods in Machine Learning II
- Introduction to Empirical Risk Minimization
- Mathematical Methods in Machine Learning II (cont'd)
- AI Engineering - Designing Machine Learning Systems
- Machine Learning Experiment Design (AISOC Workshop)
- Feature Engineering & Selection (AISOC Workshop)
- Model Evaluation (AISOC Workshop)
- Regression Deep Dive (AISOC Workshop)
- Fundamentals of High Performance AI Engineering
- Model Finetuning & Selection (AISOC Workshop)
- Introduction to AI Governance
- Unsupervised Learning Deep Dive (AISOC Workshop)
- Introduction to Model Interpretability (AISOC Workshop)
- Classification Deep Dive (AISOC Workshop)
- Neural Networks and Deep Learning (AISOC Workshop)
- Calibrating Models with Conformal Prediction (AISOC Workshop)
- AI Governance: Methods & Techniques
- Data Engineering for ML Systems (Tentative)
- LLM & RAG Evaluation
- Introduction to Machine Learning Systems
- Practical Challenges in Machine Learning