Detailed Contents

Will be updated during the semester. The slides used in the lecture will be placed here.

1. Introduction

Slides: Introduction (PDF)

1.1 Pattern Recognition

Slides: Pattern Recognition (PDF)

1.2 A Simple Example

Slides: Introductory Example (PDF)

Excursion: Probability Theory

Slides: Basics of Probability Theory (PDF)

1.3 A Probabilistic Perspective

Slides: Probabilistic Perspective (PDF)

2. Linear Models for Regression

Slides: Least squares, LMS (PDF)

3. Classification

3.1. Decision Theory

Slides: Decision Theory (PDF)

3.2 Linear Models for Classification

Slides: Discriminant functions, Generative models, Logistic regression, ... (PDF)

4. Neural Networks

Slides: Neural Networks (PDF)

5. Second Order Methods for Neural Network Training

Slides: Second Order (PDF)

6. Neural Networks - Practical Considerations

Practice, Regularization Methods

Slides: Practical Considerations (PDF, UPDATE 13.12.2013!!)

Benchmarks

Slides: Benchmarks (PDF)

Link to paper about training of deep multilayer perceptrons on MNIST [Ciresan et al., 2010].

Schmidhuber page on handwritten digit regocnition with neural networks.

Convolutional net on Yan LeCuns' Homepage.

7. Boltzmann Machines, Deep Belief Networks

Slides: Boltzmann Machines, Deep Belief Networks (PDF)

DBN in action on Hintons homepage.

Hinton, G. E. and Salakhutdinov, R. R, Science 2006 .

8. Echo State Networks

Slides: (PDF)

Science Paper by Herbert Jaeger.

Reservoir Computing Homepage with links to publications etc.