Beräkningsvetenskap: Introduktion till artificiella neuronnätverk och djupinlärning

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.

Recent development in machine learning have led to a surge of interest in artificial neural networks (ANN). New efficient algorithms and increasingly powerful hardware has made it possible to create very complex and high-performing ANNs. The process of training such complex networks has become known as deep learning and the complex networks are typically called deep neural networks. A possibility that arises in such networks is to feed them with unprocessed or almost unprocessed input information and let the algorithms automatically combine the inputs into feature-like aggregates as part of their inherent structure. This is now known under the name feature learning or representation learning

The overall aim of the course is to give students a basic knowledge of artificial neural networks and deep learning, both theoretical knowledge and how to practically use them for typical problems in machine learning and data mining. The course covers the most common models in artificial neural networks with a focus on the multi-layer perceptron. The course contains two computer exercises where the student will train and evaluate different ANN models.

https://www.cec.lu.se/sv/utbildning/kurser-och-program-i-berakningsvetenskap/artificiella-neuronnatverk