Lectures related to Computational learning theory

Offers a crash course on statistical learning theory, covering PAC-learning and loss functions.

Covers the concept of VC dimension and its implications on PAC learning.

Explores nonuniform learnability, PAC theorems, and structural risk minimization in machine learning.

Introduces orchestration graphs for designing effective learning activities.

Explores growth rate, uniform convergence, PAC learning, and distribution learning challenges.

Explores the intersection between machine learning and cryptography, focusing on safe machine learning through cryptographic tools and models.