Artificial Neural Networks and Deep Architectures (DD2437) (2nd Year of Master degree in KTH)
The course serves as a fundamental introduction to computational problems in artificial neural networks (ANNs) and provides more detailed insights into the problem of generalisation, computational nature of supervised as well as unsupervised learning in different network types and deep learning algorithms. The course offers an opportunity to develop the conceptual and theoretical understanding of computational capabilities of ANNs starting from simpler systems and progressively studying more advanced network architectures. An important objective of the course is for the students to gain practical experience of selecting, developing, applying and validating suitable networks and algorithms to effectively address a broad class of regression, classification, temporal prediction, data modelling, explorative data analytics or clustering problems.
- Lab 1: Learning and generalisation in feed-forward networks from perceptron learning to backprop
- Lab 2: Radial basis functions, competitive learning and self-organisation
- Lab 3: Hopfield networks
- Lab 4: Deep neural network architectures with autoencoders
No external ML libs allowed
(re upload)
See the summary of other courses projects here