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.

[22.09.2022] Introduction to Advanced Machine Learning, review of basics of digital image processing.

[23.09.2022] Image classification, linear classifiers and review of performance evaluation.

[29.09.2022] Image features, review of gradient descent.

[30.09.2022] Neural networks, fully connected layers, the computational graph and backpropagation.

[06.10.2022] Introduction to Pytorch.

[07.10.2022] Convolutional layers and the convolutional neural networks.

[13.10.2022] Pooling layers and visualization of ConvNets

[14.10.2022] Activation functions, data pre-processing, weight initialization, batch normalization.

[20.10.2022] More on regularization, including DropOut and data augmentation, hyper-parameter tuning.

[21.10.2022] Transfer learning and the introduction of sequence models, including temporal convolutional networks and recurrent neural networks.

[27.10.2022] Self-supervised learning.

[28.10.2022] Anomaly detection.

[03.11.2022] Backprop in RNNs, LSTMs and image captioning with RNNs.

[04.11.2022] Attention, self-attention and Transformer Networks.

[10.11.2022] Transformer Networks for images and music, including synthesis and relative self-attention.

[11.11.2022] BERT and the deployment of large-scale models with Knowledge Distillation; Human Trajectory Forecasting

[17.11.2022] Graph encoders and Graph Neural Networks

[18.11.2022] Human Pose Forecasting with Graph Convolutional Networks

[24.11.2022] Semantic segmentation, semi-automatic labelling and benchmarking

[25.11.2022] First project presentations

[1.12.2022] End-to-end Object Detection with CNN and Region Proposals

[2.12.2022] 3D Object Detection and Instance Segmentation

[15.12.2022] One- and Few-shot, and Meta-Learning for objects and people

[16.12.2022] Final Project Presentations