PIXELBANKv8.2.1
Menu
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 Chapters14 WeeksInteractive Demos

Recommended Study Path

Phase 1

Prerequisites

Foundations Study Plan

  • Python Foundations
  • NumPy & Data Wrangling
  • Mathematical Foundations

Complete the Foundations study plan first →

Phase 2

Foundations

Weeks 1-4

  • Ch 1-2: Intro & Linear Regression
  • Ch 3-4: Classification & Evaluation

Core concepts: regression, classification, metrics

Phase 3

Core ML

Weeks 5-8

  • Ch 5-6: Trees & Ensembles
  • Ch 7-8: SVM & Clustering

Decision trees, random forests, K-means

Phase 4

Advanced

Weeks 9-14

  • Ch 9-10: Neural Networks & CNNs
  • Ch 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.

All Chapters

1

Introduction to ML

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

What is ML?Types of LearningML Pipeline+1
Start Learning
2

Linear Regression

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

Simple Linear RegressionMultiple RegressionGradient Descent+1
Start Learning
3

Classification

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

Binary ClassificationLogistic RegressionMulticlass+1
Start Learning
4

Model Evaluation

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

Train/Val/Test SplitsClassification MetricsCross-Validation+1
Start Learning
PRO

Decision Trees

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

Tree BasicsSplitting CriteriaPruning+1
Pro Only
PRO

Ensemble Methods

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

Random ForestsAdaBoostGradient Boosting+1
Pro Only
PRO

Support Vector Machines

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

Linear SVMSoft MarginKernel Trick+1
Pro Only
PRO

Clustering

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

K-MeansHierarchicalDBSCAN+1
Pro Only
PRO

Neural Networks

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

Perceptrons & MLPsBackpropagationActivations+1
Pro Only
PRO

CNNs & Sequence Models

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

ConvolutionsPoolingRNNs/LSTMs+1
Pro Only
PRO

NLP Fundamentals

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

Text ProcessingEmbeddingsText Classification+1
Pro Only
PRO

Reinforcement Learning

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

MDP & RewardsQ-LearningPolicy Gradients+1
Pro Only
PRO

Generative & Production ML

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

AutoencodersVAEsGANs+1
Pro Only

Timed Tests

View all
Foundations
Ch 1-3 45 min
Evaluation & TreesPRO
Ch 4-6 45 min
SVM, Clustering & NNsPRO
Ch 7-9 45 min
Deep Learning & NLPPRO
Ch 10-11 45 min
RL & Generative ModelsPRO
Ch 12-13 45 min

Practice Problem Sets

Sharpen your skills with coding challenges and system design problems.

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