Table of contents
7 chapters · 22 sections
Learning from Data
- 1.1Supervised and unsupervised learning
- 1.2Empirical risk minimisation
- 1.3Loss functions
Linear Models
- 2.1Linear regression
- 2.2Logistic regression
- 2.3Regularisation
Optimisation
- 3.1Gradient descent
- 3.2Stochastic gradient descent
- 3.3Momentum and Adam
Neural Networks
- 4.1Perceptron
- 4.2Multilayer networks
- 4.3Activation functions
- 4.4Universal approximation
Backpropagation
- 5.1Computational graphs
- 5.2Chain rule in practice
- 5.3Automatic differentiation
Generalisation
- 6.1Bias–variance trade-off
- 6.2Overfitting and validation
- 6.3Capacity and VC dimension
Unsupervised Learning
- 7.1k-means
- 7.2PCA
- 7.3Energy-based models