v9.1.1
Menu
Sign In

From Linear Regression to Deep Learning

Machine Learning Study Plan

A comprehensive 14-week curriculum covering fundamental and advanced topics in machine learning with interactive Framer Motion visualizations.

13

chapters

52

topics

5

timed tests

PathChapters13Tests5Practice4
01

The path

4 phases, in the order we recommend.

  1. 1

    Prerequisites

    Foundations Study Plan
    Python FoundationsNumPy & Data WranglingMathematical Foundations

    Complete the Foundations study plan first →

  2. 2

    Foundations

    Weeks 1-4
    Ch 1-2: Intro & Linear RegressionCh 3-4: Classification & Evaluation

    Core concepts: regression, classification, metrics

  3. 3

    Core ML

    Weeks 5-8
    Ch 5-6: Trees & EnsemblesCh 7-8: SVM & Clustering

    Decision trees, random forests, K-means

  4. 4

    Advanced

    Weeks 9-14
    Ch 9-10: Neural Networks & CNNsCh 11-13: NLP, RL & Genertic AI

    Deep learning, NLP, reinforcement learning

Tip: Each chapter includes interactive demos, theory exercises, and practice problems.

Pro chapters (4-13) require a premium subscription.

02

Chapters

All 13 chapters are free.

CH 01

Introduction to ML

What is machine learning? Types of learning, the ML pipeline, and understanding bias-variance tradeoff.

4 topicsStart→
CH 02

Linear Regression

Your first ML algorithm: predicting continuous values with linear models, gradient descent, and regularization.

4 topicsStart→
CH 03

Classification

Binary and multiclass classification with logistic regression, sigmoid function, and feature engineering.

4 topicsStart→
CH 04

Model Evaluation

How to properly evaluate ML models: metrics, cross-validation, and hyperparameter tuning.

4 topicsStart→
CH 05

Decision Trees

Tree-based models: intuitive, interpretable, and powerful for both classification and regression.

4 topicsStart→
CH 06

Ensemble Methods

Combining multiple models: Random Forests, AdaBoost, Gradient Boosting, and model stacking.

4 topicsStart→
CH 07

Support Vector Machines

Maximum margin classifiers: linear SVM, soft margin, the kernel trick, and support vector regression.

4 topicsStart→
CH 08

Clustering

Unsupervised learning: K-Means, hierarchical clustering, DBSCAN, and cluster evaluation methods.

4 topicsStart→
CH 09

Neural Networks

Deep learning fundamentals: perceptrons, MLPs, backpropagation, activation functions, and optimizers.

4 topicsStart→
CH 10

CNNs & Sequence Models

Specialized architectures: convolutions, pooling, RNNs, LSTMs, and attention mechanisms.

4 topicsStart→
CH 11

NLP Fundamentals

Machine learning for text: preprocessing, embeddings, text classification, and transformer models.

4 topicsStart→
CH 12

Reinforcement Learning

Learning from interaction: MDPs, Q-learning, policy gradients, and deep reinforcement learning.

4 topicsStart→
CH 13

Generative & Production ML

Generative models (autoencoders, VAEs, GANs) and MLOps basics for production deployment.

4 topicsStart→
03

Timed tests

45 minutes, 13 questions, one test a day.

View all → Check Progress
TEST 01

Foundations

Ch 1-3 · 45 min

Take test→
TEST 02

Evaluation & Trees

Ch 4-6 · 45 min

Take test→
TEST 03

SVM, Clustering & NNs

Ch 7-9 · 45 min

Take test→
TEST 04

Deep Learning & NLP

Ch 10-11 · 45 min

Take test→
TEST 05

RL & Generative Models

Ch 12-13 · 45 min

Take test→
04

Practice

Problem sets that drill this plan's topics.

Machine Learning 1

Linear regression, classification, model evaluation, decision trees, ensemble methods, and SVMs.

Linear RegressionClassificationModel Evaluation+3
6 topicsView problems→

Machine Learning 2

Clustering, neural networks, CNNs, sequence models, NLP fundamentals, generative models, and dimensionality reduction.

ClusteringNeural NetworksCNNs & Sequences+3
6 topicsView problems→
System design

ML System Design 1

Design real-world ML systems — pipelines, architecture decisions, and structural design patterns.

System Architecture
1 topicView problems→
System design

ML System Design 2

Advanced ML system design challenges covering deployment, scalability, and production MLOps.

System Architecture
1 topicView problems→

Curriculum designed to take you from ML fundamentals to advanced deep learning and production deployment.