v9.1.1
Menu
Sign In

Essential Prerequisites for CV & ML Study Plans

Foundations

Set up your environment, then master Python, NumPy, Mathematics, Probability, and PyTorch — the essential building blocks for both Computer Vision and Machine Learning.

7

chapters

57

topics

2

timed tests

PathChapters7Tests2
01

The path

5 phases, in the order we recommend.

  1. 1

    Environment

    Chapter 0
    OS & Terminal SetupVS Code & Python InstallGit, Jupyter & Docker

    Get your development tools ready

  2. 2

    Programming

    Chapter 1
    Python Core LanguageData Structures & OOPNumPy/Pandas & Scikit-learn Intro

    Essential Python for AI/ML

  3. 3

    Data Skills

    Chapter 2
    NumPy Arrays & BroadcastingPandas DataFramesData Cleaning & Preparation

    Master numerical computing

  4. 4

    Mathematics

    Chapters 3-5
    Linear Algebra & CalculusProbability & StatisticsAdvanced Linear Algebra

    Essential math for ML/CV/NLP

  5. 5

    Deep Learning Framework

    Chapter 6
    Tensors, Autograd & nn.ModuleDataLoaders & the Training LoopCustom Autograd, Mixed Precision & torch.compile

    Build and train models in PyTorch

Tip: Each chapter includes interactive demos, worked examples, and exercises.

Complete these before starting the CV or ML study plans.

02

Chapters

All 7 chapters are free.

CH 00

Development Setup (Optional)

Set up the ideal ML development environment: OS, terminal, VS Code, Python, Git, Jupyter, Docker, and AI coding assistants.

8 topicsStart→
CH 01

Python Foundations

Essential Python programming for AI: variables, data structures, control flow, functions, classes, NumPy/Pandas basics, and scikit-learn introduction.

9 topicsStart→
CH 02

NumPy & Data Wrangling

Master NumPy arrays, Pandas DataFrames, broadcasting, reshaping, statistics, linear algebra, and data preprocessing techniques.

9 topicsStart→
CH 03

Mathematical Foundations

Essential mathematics: linear algebra, probability & statistics, information theory, calculus for optimization, matrix decompositions, and PCA.

7 topicsStart→
CH 04

Probability & Statistics

Deep dive into probability theory, distributions, estimation, hypothesis testing, Bayesian inference, and sampling methods for ML.

8 topicsStart→
CH 05

Linear Algebra

Deep dive into vector spaces, orthogonality, projections, least squares, spectral theory, and numerical methods for ML/CV/NLP.

8 topicsStart→
CH 06

PyTorch Fundamentals

From tensors to training at scale: tensor operations, autograd, nn.Module, DataLoaders, the training loop, custom autograd functions and hooks, mixed precision, and torch.compile.

8 topicsStart→
03

Timed tests

45 minutes, 13 questions, one test a day.

View all → Check Progress
TEST 01

Foundations Test

Ch 1-3 · 45 min

Take test→
TEST 02

Probability & Statistics

Ch 4 · 45 min

Take test→

Where to Go Next

ML Study Plan

From Linear Regression to Deep Learning

CV Study Plan

Computer Vision: Algorithms and Applications

Master these foundations before moving on to the CV and ML study plans.