PAC Learning Courses and Certifications

Squid: Schools for Quantum Information Development

Provable Advantage in Quantum PAC Learning

Discover groundbreaking research on quantum PAC learning, exploring provable advantages over classical methods with square root improvements in sample complexity and theoretical quantum information science.

• YouTube
• 24 minutes
• On-Demand
• Free Video

Institute for Pure & Applied Mathematics (IPAM)

Learning in a Dynamic World: From PAC to Prospective Learning Theory

Explore dynamic learning theory and its evolution beyond PAC learning, examining how AI systems can adapt to changing data distributions and goals while maintaining performance over time.

• YouTube
• 51 minutes
• On-Demand
• Free Video

Machine Learning

Learn about machine learning, the area of artificial intelligence (AI) that is concerned with computational artifacts that modify and improve performance through experience.

• edX
• 14 weeks, 8-10 hours a week
• On-Demand
• Free Online Course (Audit)

Simons Institute

Studying Generalization in Deep Learning via PAC-Bayes

Explore PAC-Bayes theory's application to deep learning generalization, focusing on risk bounds, optimal priors, and SGD prediction for neural networks.

• YouTube
• 45 minutes
• On-Demand
• Free Video

Institute for Advanced Study

PAC-Bayesian Approaches to Understanding Generalization in Deep Learning - Gintare Dziugaite

Explore PAC-Bayesian approaches for understanding generalization in deep learning, covering risk bounds, optimal priors, and data-dependent techniques for neural networks.

• YouTube
• 32 minutes
• On-Demand
• Free Video

NDC Conferences

Reinforcement Learning - Pac-Man

Explore reinforcement learning through building a Pac-Man-beating agent. Gain insights into Q-learning, deep Q-learning with neural networks, and practical implementation using libraries like Keras.

• YouTube
• 1 hour 1 minute
• On-Demand
• Conference Talk

Learning Event Streaming Processing with Pac-Man

Explore event streaming processing through an interactive Pac-Man demo, showcasing real-time data handling and practical applications in modern software architecture.

• YouTube
• 55 minutes
• On-Demand
• Free Video

UofU Data Science

Machine Learning - Spring 2024

Master fundamental ML algorithms from decision trees to neural networks, covering theory, implementation, and practical applications for real-world problem solving.

• YouTube
• 1 day 11 hours 22 minutes
• On-Demand
• Free Video

UofU Data Science

Machine Learning - Spring 2023

Dive into comprehensive machine learning fundamentals covering supervised learning, decision trees, linear models, perceptron, SVMs, neural networks, and Bayesian methods.

• YouTube
• 1 day 13 hours 23 minutes
• On-Demand
• Free Video

Alan Turing Institute

Learning Logically Defined Hypotheses - Martin Grohe, RWTH Aachen University

Explore a declarative framework for machine learning using logic-defined hypotheses, discussing learnability results for various logics over strings, trees, and graphs.

• YouTube
• 45 minutes
• On-Demand
• Free Video

Paul G. Allen School

Statistical Learning IV - Robert Schapire, Microsoft Research

Explore statistical learning with Robert Schapire, covering expected value theorems, ghost samples, PAC learning, and finite hypothesis spaces in this comprehensive lecture.

• YouTube
• 1 hour 1 minute
• On-Demand
• Free Video

IAS | PCMI Park City Mathematics Institute

Overview of Quantum Learning Theory - Lecture 1

Dive into quantum learning theory fundamentals, exploring Boolean functions, quantum states, and circuit distributions with expert guidance on core concepts and proof techniques - no prior quantum knowledge needed.

• YouTube
• 54 minutes
• On-Demand
• Free Video

Institute for Advanced Study

Characterizations of PAC Learnability

Explore key characterizations of PAC learnability in machine learning theory with insights from postdoctoral researcher Nataly Brukhim.

• YouTube
• 15 minutes
• On-Demand
• Free Video

Simons Institute

Learning Probability Distributions: What Can and Can't Be Done

Explore statistical learning, focusing on guaranteed generalizations from finite samples and characterizing learnable distribution families. Gain insights into modern paradigms in generalization.

• YouTube
• 1 hour 12 minutes
• On-Demand
• Free Video

Simons Institute

Distribution Learning Meets Graph Structure Sampling

Explore the connection between PAC-learning of graphical models and efficient graph structure sampling, leveraging online learning algorithms for new insights in high-dimensional distribution learning.

• YouTube
• 27 minutes
• On-Demand
• Free Video