Details

Contents
Preface
1 Symbolic Classification and Nearest Neighbour Classification
1.1 Symbolic Classification
1.2 Nearest Neighbour Classification
2 Separating Planes and Linear Programming
2.1 Finding a Separating Hyperplane
2.2 Testing for feasibility of linear constraints
2.3 Linear Programming
MATLAB example
2.4 Conclusion
3 Separating Margins and Quadratic Programming
3.1 Quadratic Programming
3.2 Maximum Margin Separator Planes
3.3 Slack Variables
4 Dualization and Support Vectors
4.1 Duals of Linear Programs
4.2 Duals of Quadratic Programs
4.3 Support Vectors
5 Lagrange Multipliers and Duality
5.1 Multidimensional functions
5.2 Support Vector Expansion
5.3 Support Vector Expansion with Slack Variables
6 Kernel Functions
6.1 Feature Spaces
6.2 Feature Spaces and Quadratic Programming
6.3 Kernel Matrix and Mercer’s Theorem
6.4 Proof of Mercer’s Theorem
Step 1 – Definitions and Prerequisites
Step 2 – Designing the right Hilbert Space
Step 3 – The reproducing property
7 The SMO Algorithm
7.1 Overview and Principles
7.2 Optimisation Step
7.3 Simplified SMO
8 Regression
8.1 Slack Variables
8.2 Duality, Kernels and Regression
8.3 Deriving the Dual form of the QP for Regression
9 Perceptrons, Neural Networks and Genetic Algorithms
9.1 Perceptrons
Perceptron-Algorithm
Perceptron-Lemma and Convergence
Perceptrons and Linear Feasibility Testing
9.2 Neural Networks
Forward Propagation
Training and Error Backpropagation
9.3 Genetic Algorithms
9.4 Conclusion
10 Bayesian Regression
10.1 Bayesian Learning
10.2 Probabilistic Linear Regression
10.3 Gaussian Process Models
10.4 GP model with measurement noise
Optimization of hyperparameters
Covariance functions
10.5 Multi-Task Gaussian Process (MTGP) Models
11 Bayesian Networks
Propagation of probabilities in causal networks
Appendix – Linear Programming
A.1 Solving LP0 problems
A.2 Schematic representation of the iteration steps
A.3 Transition from LP0 to LP
A.4 Computing time and complexity issues
References
Index

Künstliche Intelligenz wird unser Leben nachhaltig verändern – sowohl im Job als auch im Privaten. Doch wie funktioniert maschinelles Lernen eigentlich genau? Dieser Frage gehen zwei Lübecker Professoren in ihrem englischsprachigen Lehrbuch nach. Definitionen sind im Buch hervorgehoben und Aufgaben laden die LeserInnen zum Mitdenken ein.
Das Lehrbuch richtet sich an Studierende der Informatik, Technik und Naturwissenschaften, insbesondere aus den Bereichen Robotik, Artificial Intelligence und Mathematik.
Artificial intelligence will change our lives forever - both at work and in our private lives. But how exactly does machine learning work?
Two professors from Lübeck explore this question. In their English textbook they teach the necessary basics for the use of Support Vector Machines, for example, by explaining linear programming, the Lagrange multiplier, kernels and the SMO algorithm. They also deal with neural networks, evolutionary algorithms and Bayesian networks. Definitions are highlighted in the book and tasks invite readers to actively participate.
The textbook is aimed at students of computer science, engineering and natural sciences, especially in the fields of robotics, artificial intelligence and mathematics.