Lecture 1 – Introduction to Deep Learning

neural network theory, output units, hidden units, activation functions

Lecture 2 – Optimization and Regularization

stochastic optimization (SGD, ADAM,…), regularization

Lecture 3 – CNNs

CNN building blocks, CNN architectures, Image classification, Object detection, Segmentation, Denoising

Lecture 4 – Transformers, Large Language Models

RNN, LSTM, GRU, Self-Attention, Cross-Attention, Transformers, Vision Transformers

Lecture 5 – Generative models

GAN, VAE, Diffusion models, Implicit networks (SIREN, NeRF)