Here is a brief diary of topics discussed in classes.

Slides and coding scripts are distributed after each lecture via the Google groups mailing-list. Refer to the home page on how to subscribe.

[25.09.2023] Introduction to the course, review introduction of machine learning and computer computer vision.

[29.09.2023] Review of the basics of digital image processing and of neural networks, specifically fully connected layers, the computational graph, backpropagation, and Pytorch.

[2.10.2023] Introduction to Embodied AI.

[9.10.2023] Convolutional layers and the convolutional neural networks.

[13.10.2023] Pooling layers , visualization of ConvNets,  Activation functions, data pre-processing.

[16.10.2023] Weight initialization, and batch normalization.

[20.10.2023] More on regularization, including DropOut and data augmentation, hyper-parameter tuning; transfer learning.

[23.10.2023] Sequence modelling with temporal convolutional networks and introduction to recurrent neural networks.

[27.10.2023] Backprop in RNNs, LSTMs and image captioning with RNNs.

[30.10.2023] Attention and self-attention

[3.11.2023] Positional encoding and Transformer Networks, including the application to images

[6.11.2023] Transformer Networks for music and relative self-attention, BERT

[10.11.2023] BERT and the deployment of large-scale models with Knowledge Distillation; Human Trajectory Forecasting

[13.11.2023] Graph encoders and Graph Neural Networks

[17.11.2023] Graph Convolutional Networks

[20.11.2023] Semantic segmentation

[24.11.2023] Object Detection

[27.11.2023] Instance Segmentation

[1.12.2023] First Project Presentations

[4.12.2023] One--shot learning, object and person search.

[11.12.2023] Self-supervised learning.

[15.12.2023] Generative AI via AE, VAE, GAN and (Latent) Diffusion Models.

[18.12.2023] Semantic search; Hyperbolic deep learning for hierarchical data and for estimating uncertainty.

[22.12.2023] Final Project Presentations.