A knowledge base distilled from 16 books
AI/ML, from intuition to implementation.
Machine learning foundations, neural networks, transformers, LLMs, RAG, evaluation, production ML, and responsible AI — explained through practical mental models for developers.
- Domains
- 7
- Topics
- 37
- Graph edges
- 122
AI/ML FoundationsThe vocabulary and mental models behind machine learning: data, labels, loss, optimization, generalization, and evaluation.Classical Machine LearningThe practical non-deep-learning toolbox: linear models, trees, ensembles, clustering, feature engineering, and validation.Deep LearningNeural networks as representation learners: layers, backpropagation, optimizers, regularization, embeddings, and modern architectures.LLMs & Generative AIHow large language models work and how to reason about tokens, context, pretraining, prompting, RAG, tools, and agents.Applied AI EngineeringThe developer-facing craft of shipping AI features: structured outputs, retrieval, evaluation, latency, cost, reliability, and observability.Production ML & MLOpsThe systems side of ML: pipelines, serving, online inference, training-serving skew, monitoring, experiments, and rollout safety.Responsible AIBias, privacy, explainability, prompt injection, provenance, and human review treated as engineering constraints, not side quests.
Distilled from
- Artificial Intelligence: A Modern ApproachStuart Russell, Peter Norvig
- CS229: Machine LearningStanford University
- An Introduction to Statistical Learning with PythonGareth James, Daniela Witten, Trevor Hastie, Rob Tibshirani, Jonathan Taylor
- Mathematics for Machine LearningMarc Peter Deisenroth, A. Aldo Faisal, Cheng Soon Ong
- Deep LearningIan Goodfellow, Yoshua Bengio, Aaron Courville
- Dive into Deep LearningAston Zhang, Zachary C. Lipton, Mu Li, Alexander J. Smola
- Machine Learning Crash CourseGoogle
- scikit-learn User Guidescikit-learn developers
- Hugging Face LLM CourseHugging Face
- OpenAI API DocumentationOpenAI
- Claude Prompt Engineering and Evaluation DocsAnthropic
- Rules of Machine LearningMartin Zinkevich, Google
- Made With MLGoku Mohandas / Anyscale
- Attention Is All You NeedAshish Vaswani et al.
- Training Language Models to Follow Instructions with Human FeedbackLong Ouyang et al.
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis et al.