## Intensive course on neural networks (Göttingen)

This short course introduces the use of artificial neural networks in machine learning. The course is aimed at engineers and natural scientists. The focus is on supervised learning with multi-layer perceptron networks, because this method has recently become very popular in science and technology. I describe the network layout, how to train such networks with stochastic gradient descent, and describe recent developments in the field (*deep learning*). I conclude with a discussion of current questions and applications. This course is based on Chapters 5 to 10 of *Machine learning with neural networks*. I also offer homework problems that illustrate the learning goals. These will be made available in the online system OpenTA.

### Registration

**Note.** Please register here before the first lecture. Email Bernhard Mehlig if you encounter problems.

### Prerequisites

Basic linear algebra, analysis, and programming. Test your skills with a quiz at the OpenTA site.

### Contents and schedule

Thu Jan 11 | 14:00- 15:45 | Introduction and overview | |

16:15 - 18:00 | Perceptrons | Chapter 5 | |

Fri Jan 12 | 14:00 - 15:45 | Training deep networks | Chapter 6 |

16:15 - 18:00 | Introduction to Exercises | OpenTA | |

Thu Jan 18 | 14:00 - 15:45 | Training deep networks | Chapter 7 |

Convolutional networks | Chapter 8 | ||

16:15 - 18:00 | Unsupervised learning | Chapter 10 | |

Fri Jan 19 | 14:00 - 15:45 | Recurrent networks | Chapter 9 |

16:15 - 18:00 | Machine translation & transformers |

### Literature

B. Mehlig, *Machine learning with neural networks*, Cambridge University Press (2021)

B. Mehlig, *Exercise solutions for Machine learning with neural networks* (2023)