Skip to content
learn
  1. Learn
  2. Machine Learning

Machine Learning

From "what is a model" to training, shipping and monitoring ML systems in production.

18 modules 124 lessons 27 hours 0 completed

00 Orientation 01 Mathematics for ML (o... 02 Data: the most import... 03 Regression 04 Classification 05 Model Evaluation and... 06 Trees and Ensembles 07 Unsupervised Learning 08 Neural Networks and D... 09 Computer Vision 10 Sequences and Natural... 11 Time Series and Forec... 12 Recommender Systems a... 13 Reinforcement Learning 14 Generative Models 15 MLOps and Production... 16 Responsible ML 17 ML System Design Case...

ML-M00

Orientation

  1. What is machine learning? Beginner . 10 min
  2. Types of learning Beginner . 10 min
  3. The ML project lifecycle Beginner . 12 min
  4. Your toolkit: Python, NumPy, pandas, scikit-learn, PyTorch Beginner . 15 min

ML-M01

Mathematics for ML (only what you need, visually)

  1. Vectors and vector spaces Beginner . 12 min
  2. Matrices and linear transformations Beginner . 14 min
  3. Eigenvectors, eigenvalues and SVD Intermediate . 15 min
  4. Derivatives and the chain rule Beginner . 14 min
  5. Probability fundamentals Beginner . 15 min
  6. Distributions you will meet Beginner . 12 min
  7. Statistics: sampling, CLT and confidence intervals Intermediate . 15 min
  8. Hypothesis testing and p-values Intermediate . 14 min
  9. Optimization basics Intermediate . 12 min
  10. Information theory for ML Intermediate . 12 min

ML-M02

Data: the most important part

  1. Data types and datasets Beginner . 10 min
  2. Data collection and labeling Beginner . 12 min
  3. Exploratory data analysis Beginner . 15 min
  4. Data cleaning Beginner . 12 min
  5. Feature engineering Intermediate . 18 min
  6. Feature selection Intermediate . 10 min
  7. Train, validation and test splits Beginner . 10 min
  8. Data leakage Intermediate . 12 min
  9. Imbalanced data Intermediate . 12 min

ML-M03

Regression

  1. Linear regression intuition Beginner . 14 min
  2. Solving linear regression: normal equation and gradient descent Intermediate . 15 min
  3. Gradient descent, the engine of ML Beginner . 18 min
  4. Polynomial regression and basis functions Intermediate . 10 min
  5. Regularization: ridge, lasso, elastic net Intermediate . 14 min
  6. Regression metrics Beginner . 10 min

ML-M04

Classification

  1. Logistic regression Beginner . 15 min
  2. k-Nearest Neighbours Beginner . 10 min
  3. Naive Bayes Intermediate . 10 min
  4. Support Vector Machines and kernels Intermediate . 15 min
  5. Classification metrics Beginner . 16 min
  6. Probability calibration Advanced . 10 min
  7. Multi-class and multi-label classification Intermediate . 10 min

ML-M05

Model Evaluation and Selection

  1. Bias, variance, underfitting and overfitting Beginner . 14 min
  2. Cross-validation Intermediate . 12 min
  3. Hyperparameter tuning Intermediate . 12 min
  4. Learning curves and baselines Intermediate . 10 min
  5. Offline vs online evaluation and A/B tests Intermediate . 14 min

ML-M06

Trees and Ensembles

  1. Decision trees Beginner . 14 min
  2. Bagging and random forests Intermediate . 12 min
  3. Boosting: AdaBoost to gradient boosting Intermediate . 16 min
  4. XGBoost, LightGBM and CatBoost in practice Intermediate . 14 min
  5. Stacking and blending Advanced . 8 min
  6. Feature importance and SHAP Intermediate . 12 min

ML-M07

Unsupervised Learning

  1. k-means clustering Beginner . 14 min
  2. Hierarchical clustering and DBSCAN Intermediate . 12 min
  3. Gaussian mixture models and EM Advanced . 12 min
  4. Principal Component Analysis Intermediate . 14 min
  5. t-SNE and UMAP Intermediate . 10 min
  6. Anomaly detection Intermediate . 12 min
  7. Association rules and market basket analysis Beginner . 8 min

ML-M08

Neural Networks and Deep Learning Foundations

  1. The perceptron and the artificial neuron Beginner . 12 min
  2. Multi-layer networks Beginner . 14 min
  3. Activation functions Beginner . 10 min
  4. Loss functions Beginner . 10 min
  5. Forward pass by hand Beginner . 12 min
  6. Backpropagation Intermediate . 20 min
  7. Autograd and your first PyTorch training loop Intermediate . 15 min
  8. Optimizers: SGD, momentum, RMSProp, Adam, AdamW Intermediate . 14 min
  9. Learning rate schedules and warmup Intermediate . 8 min
  10. Weight initialization and normalization Advanced . 12 min
  11. Regularization for deep nets Intermediate . 10 min
  12. Vanishing and exploding gradients, residual connections Advanced . 12 min
  13. Debugging neural network training Intermediate . 12 min

ML-M09

Computer Vision

  1. Images as tensors Beginner . 8 min
  2. Convolutions Beginner . 15 min
  3. Pooling and CNN architecture Beginner . 12 min
  4. Landmark CNNs: LeNet to ResNet Intermediate . 14 min
  5. Transfer learning and fine-tuning Intermediate . 12 min
  6. Data augmentation Beginner . 8 min
  7. Object detection Advanced . 15 min
  8. Image segmentation Advanced . 12 min
  9. Vision transformers Advanced . 12 min

ML-M10

Sequences and Natural Language Processing

  1. Text preprocessing and tokenization basics Beginner . 10 min
  2. Bag of words and TF-IDF Beginner . 10 min
  3. Word embeddings Intermediate . 14 min
  4. Recurrent neural networks Intermediate . 14 min
  5. LSTM and GRU Intermediate . 14 min
  6. Seq2seq and attention Intermediate . 14 min

ML-M11

Time Series and Forecasting

  1. Time series fundamentals Beginner . 12 min
  2. Stationarity and classical models Intermediate . 15 min
  3. Prophet and modern forecasting libraries Intermediate . 10 min
  4. ML and deep learning for forecasting Advanced . 14 min
  5. Backtesting and forecast evaluation Intermediate . 10 min

ML-M12

Recommender Systems and Ranking

  1. Recommender fundamentals Beginner . 10 min
  2. Collaborative filtering and matrix factorization Intermediate . 15 min
  3. Two-tower retrieval and embedding-based retrieval Advanced . 14 min
  4. Learning to rank Advanced . 14 min
  5. Graph-based recommendations Advanced . 10 min
  6. Cold start, diversity and feedback loops Advanced . 10 min

ML-M13

Reinforcement Learning

  1. RL fundamentals and MDPs Intermediate . 14 min
  2. Multi-armed bandits Intermediate . 12 min
  3. Q-learning Intermediate . 14 min
  4. Deep Q-Networks Advanced . 12 min
  5. Policy gradients and actor-critic, PPO Advanced . 15 min
  6. RL in the real world Advanced . 8 min

ML-M14

Generative Models

  1. Autoencoders Intermediate . 12 min
  2. Variational autoencoders Advanced . 14 min
  3. Generative adversarial networks Advanced . 12 min
  4. Diffusion models Advanced . 16 min

ML-M15

MLOps and Production ML

  1. Framing ML problems for products Intermediate . 12 min
  2. ML system architecture overview Intermediate . 14 min
  3. Experiment tracking and reproducibility Beginner . 10 min
  4. Feature stores and training-serving skew Advanced . 12 min
  5. Training pipelines and orchestration Intermediate . 10 min
  6. Model serving patterns Intermediate . 14 min
  7. Monitoring, drift and retraining Intermediate . 14 min
  8. Model compression Advanced . 12 min
  9. GPUs and distributed training Advanced . 16 min

ML-M16

Responsible ML

  1. Fairness and bias Intermediate . 12 min
  2. Explainability Intermediate . 10 min
  3. Privacy-preserving ML Advanced . 12 min
  4. Robustness and adversarial examples Advanced . 10 min

ML-M17

ML System Design Case Studies

  1. Design a fraud detection system Advanced . 22 min
  2. Design an ETA prediction system Advanced . 20 min
  3. Design a feed ranking system Advanced . 22 min
  4. Design a search ranking system Advanced . 22 min
  5. Design an ad click-through-rate prediction system Advanced . 20 min
  6. Design a spam / content moderation classifier Advanced . 18 min
  7. Design a demand forecasting system Advanced . 18 min
  8. Design a visual search system Advanced . 18 min

Learning paths with Machine Learning lessons