+- MKLab (https://mklab.gr)
+-- Forum: [INDEX] (https://mklab.gr/forumdisplay.php?fid=1)
+--- Forum: ARTFICIAL INTELLIGENCE (AI) (https://mklab.gr/forumdisplay.php?fid=5)
+---- Forum: COURSES-LECTURES (https://mklab.gr/forumdisplay.php?fid=38)
+---- Thread: UW CSE543: Deep Learning (/showthread.php?tid=1561)
UW CSE543: Deep Learning - mklabgr - 08-11-2026
UW CSE543: Deep Learning
Summary
The University of Washington’s CSE 543 course provides an advanced introduction to the theory and practice of deep learning, beginning with neural-network fundamentals and approximation theory before moving into optimization topics such as backpropagation, advanced optimizers, gradient descent, and global convergence. It then examines generalization in deep learning, including neural tangent kernels, double descent, implicit bias, and the relationship between neural networks and kernels.
The course also covers major neural-network architectures—CNNs, RNNs, LSTMs, and attention mechanisms—followed by representation learning and generative AI, including self-supervised and contrastive learning, CLIP, GANs, VAEs, energy-based models, normalizing flows, score-based models, and diffusion models. It concludes with deep reinforcement learning and decision transformers, followed by student project presentations.
COURSE