Deep learning and artificial neural networks have in recent years become very popular and led to impressive results for difficult computer science problems such as classifying objects in images, speech recognition and playing Go. This course gives an introduction to artificial neural networks and deep learning, both theoretical and practical knowledge. 

Contents

The course covers the most common models in artificial neural networks with a focus on the multi-layer perceptron. The course also provides an introduction to deep learning. Selected topics:

Feed-forward neural networks

The simple perceptron and the multi-layer perceptron, choice of suitable error functions and techniques to minimize them, how to detect and avoid overtraining, ensembles of neural networks and techniques to create them, Bayesian training of multi-layer perceptrons.

Recurrent neural networks

Simple recurrent networks and their use in time series analysis, fully recurrent for both time series analysis and associative memories (Hopfield model), the simulated annealing optimization technique.

Deep learning

Overview of deep learning, convolutional neural networks for classification of images, different techniques to avoid overtraining in deep networks, techniques to pre-train deep networks, the attention mechanism and transformers.

Teachers

Mattias Ohlsson, Patrik Edén

Course dates

Nov 4, 2024 - Jan 8, 2025

Course info

Course page with course plan: canvas.education.lu.se/courses/29307

Schedule: cloud.timeedit.net/lu/web/n1/ri1Y4X2QQ5wZ96Qv75075105yYY38ZQ7.html

Note the course is given in together with the MSc course BERN04/EXTQ41

Registration

Registration is now closed.

Registration will close on 18th October 2024