- Learn
- 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
ML-M00
Orientation
ML-M01
Mathematics for ML (only what you need, visually)
- Vectors and vector spaces
- Matrices and linear transformations
- Eigenvectors, eigenvalues and SVD
- Derivatives and the chain rule
- Probability fundamentals
- Distributions you will meet
- Statistics: sampling, CLT and confidence intervals
- Hypothesis testing and p-values
- Optimization basics
- Information theory for ML
ML-M02
Data: the most important part
ML-M03
Regression
ML-M04
Classification
ML-M05
Model Evaluation and Selection
ML-M06
Trees and Ensembles
ML-M07
Unsupervised Learning
ML-M08
Neural Networks and Deep Learning Foundations
- The perceptron and the artificial neuron
- Multi-layer networks
- Activation functions
- Loss functions
- Forward pass by hand
- Backpropagation
- Autograd and your first PyTorch training loop
- Optimizers: SGD, momentum, RMSProp, Adam, AdamW
- Learning rate schedules and warmup
- Weight initialization and normalization
- Regularization for deep nets
- Vanishing and exploding gradients, residual connections
- Debugging neural network training
ML-M09
Computer Vision
ML-M10
Sequences and Natural Language Processing
ML-M11
Time Series and Forecasting
ML-M12
Recommender Systems and Ranking
ML-M13
Reinforcement Learning
ML-M14
Generative Models
ML-M15
MLOps and Production ML
ML-M16
Responsible ML
ML-M17