Designing Machine Learning Applications

Contents
Preface
- About the Author
- About DMLA
Mathematical Foundations
- Linear Algebra
  - Vector Basics
  - Matrix Basics
- Calculus
  - Limits, Derivatives, and Differentials
  - Multivariate Functions and Composite Function Differentiation
- Statistics and Probability
  - Probability Basics
  - Statistical Inference
Classical Statistical Learning
- Linear Models
- Bayesian Methods
- Support Vector Machines
  - Support Vector Machine
  - Kernel Trick
- Decision Trees and Ensembles
- Unsupervised Learning
  - Clustering
  - Dimensionality Reduction
Neural Networks and Deep Learning
- Neural Network Architectures
- Optimization
  - Gradient Descent
  - Adaptive Optimizers
- Deep Network Stability
- Convolutional Neural Networks
- Generative Models
- Sequence Models
The Language Model Singularity
- Transformer Architecture
- Pretraining and Fine-Tuning
- Alignment Training
- Reasoning Capabilities
- Multimodal Fusion and Safety
AI Infrastructure and Engineering
- Model Serving
- MLOps Practices
Agentic Application Systems
- Vector Retrieval and RAG
- Building Agent Applications
Appendix
- Building the Sandbox Environment
- NumPy Practice

Last Updated:

Contributors: icyfenix, Claude, Claude Opus 4.6