Deep Learning and Computer Vision, HS 2026
1
Introduction to machine learning
June 8, 2026
1
Introduction to machine learning
June 8, 2026
Intro to machine learning, AI history, probabilistic foundations of ML, the Bayes rule, the coin tossing example, priors and conjugate priors.
2
Linear models and introduction to neural networks
June 9, 2026
2
Linear models and introduction to neural networks
June 9, 2026
Bayesian inference, linear regression, logistic regression, and their role in DL. From the brain to artificial neural networks.
3
Backpropagation and gradient descent algorithms
June 10, 2026
3
Backpropagation and gradient descent algorithms
June 10, 2026
Computational graphs and backpropagation. Gradient descent, stochastic gradient descent, SGD variants and adaptive SGD algorithms.
4
Convolutional neural networks
June 12, 2026
4
Convolutional neural networks
June 12, 2026
Convolutional neural networks: idea, formalization, pooling,
5
Convolutional architectures, recurrent neural networks
June 16, 2026
6
LSTM, attention mechanisms, Transformers
June 17, 2026
7
Vision transformers, object detection from R-CNN to DETR
June 22, 2026
8
Generative models, GANs, WGAN and AAE
June 23, 2026
9
VAE and diffusion models
June 24, 2026