⌘K
ENES
GitHub
phase~1 min readUpdated 2026-07-19#phase#foundations

Phase 01 Foundations

Foundations define what a system can represent, infer, optimize, and verify. They include mathematical objects, executable computation, explicit reasoning algorithms, statistical learning assumptions, and the data-generating process.

Mental model

Representation defines what can be expressed; probability and data define uncertainty; objectives define preference; computation and algorithms determine what can actually be solved.

Roadmap

Exit criteria

You can define shapes and distributions, compute a gradient update, trace reverse-mode autodiff, compare search with learned policies, design a valid split, identify leakage and shift, and state what the data cannot support.

Connects to: Phase 00 — Orientation · Phase 02 — Learning and Models

Core sources

Related notes

Learning FoundationsEvaluation metrics & what they hideAccuracy lies on imbalanced data. Precision, recall, F1, ROC-AUC — what each measures, and how to pick the metric that matches the cost of being wrong.Learning FoundationsFeatures, representations & the curse of dimensionalityModels don't see the world — they see features. How representation quality decides everything, and why high dimensions are weird.Learning FoundationsGeneralization, overfitting & the bias–variance tradeoffA model is only useful if it works on data it never saw. Overfitting, underfitting, and the tradeoff that governs both.Learning FoundationsHow learning works: loss, objective, and ERMEvery model that "learns" is minimizing a loss function over data. Understand that loop and most of ML stops being magic.