Inhaltsangabe
Chapter 1 - A Brief Review on Machine Learning
1.1 Machine Learning definition
1.2 Main types of learning
1.3 Supervised learning
1.4 How a supervised algorithm learns?
1.5 Illustrating the Supervised Learning
1.51. The Perceptron
1.5.2 Multilayer Perceptron
1.6 Concluding Remarks
Chapter 2 - Statistical Learning Theory
2.1 Motivation
2.2 Basic concepts
2.2.1 Probability densities and joint probabilities
2.2.2 Identically and independently distributed data2.2.3 Assumptions considered by the Statistical Learning Theory
2.2.4 Expected risk and generalization
2.2.5 Bounds for generalization with a practical example
2.2.6 Bayes risk and universal consistency
2.2.7 Consistency, overfitting and underfitting
2.2.8 Bias of classification algorithms
2.3 Empirical Risk Minimization Principle
2.3.1 Consistency and the ERM Principle
Die Inhaltsangabe kann sich auf eine andere Ausgabe dieses Titels beziehen.
