BERN04/EXTQ41/NMV012F- Introduction to Artificial Neural Networks and Deep Learning

Welcome

BERN04/EXTQ41/NMV012F: Introduction to Artificial Neural Networks and Deep Learning, 7.5 credits

Advanced level (second cycle) course in computational science, course code BERN04, given by CEC. Also available as EXTQ41 (LTH) and NMV012F (phd). The course replaces FYTN14/EXTQ40/NTF005F with minor differences.

Note: this page contains general information about the course. If you are a student on the course you have to log in to the Canvas portal to the left to see the current course instance. The course calendar and course stream on this page are not active.

Contents​​

Explore ANN. AI-generated.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.

General information

Course literature

  • Printed lecture notes "Introduction to Artificial Neural Networks and Deep Learning", M. Ohlsson and P. Edén, available at Media-Tryck, and as pdf on course website.
  • Supplemental online literature "Deep Learning Book Links to an external site."

Teachers

Schedule

Through Time Edit. Information about the compulsory introductory meeting can be found in TimeEdit.

Application

Apply through antagning.se Links to an external site.