Deep learning, language models, reinforcement learning, statistical learning theory, representation learning, and vision.
Structural connections linking subfields, mathematical foundations, and courses across disciplines.
Receptive fields in visual cortex, Hebbian synaptic plasticity, and predictive coding inspired convolutional architectures, attention mechanisms, and representation learning.
MIT · Phillip Isola & Sara Beery
This course provides a rigorous, in-depth exploration of deep learning fundamentals, including neural network architectures, optimization algorithms, and regularization techniques, forming the theoretical core of the subfield.
Simons Institute (UC Berkeley) · Leslie Valiant, Ron Rivest & Jon Kleinberg
This research-level course delves into the mathematical and computational principles underpinning modern machine learning, covering statistical learning theory, generalization bounds, and algorithmic foundations, defining the subfield.
No matching lectures in this category
Clear active subfield or level filters to view the full discipline archive.