Computational Learning Theory Courses and Certifications

UofU Data Science

Computational Learning Theory and PAC Learning Models - Lecture 11

Explore formal models of learnability and the PAC learning framework to understand theoretical foundations of machine learning algorithms and their capabilities.

• YouTube
• 1 hour 19 minutes
• On-Demand
• Free Video

UofU Data Science

Introduction to Computational Learning Theory - Lecture 12

Explore fundamental concepts of computational learning theory and theoretical frameworks that underpin machine learning algorithms and their effectiveness.

• YouTube
• 1 hour 8 minutes
• On-Demand
• Free Video

UofU Data Science

Machine Learning: Computational Learning Theory and Batch Learning - Lecture 12

Delve into formal models of learnability, focusing on batch learning concepts, mistake bound models, and PAC learning theory in machine learning applications.

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

The 3rd TBSI Workshop on Learning Theory

Explore cutting-edge developments in machine learning theory, optimization algorithms, and statistical inference through expert-led discussions and research presentations.

• XuetangX
• On-Demand
• Free Online Course

Explore computational learning theory, focusing on binary classification and incremental learning models, with insights into various AI approaches and research areas.

• openHPI
• 3 weeks
• On-Demand
• Free Online Course

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

BIMSA

Educability: Defining and Simulating Human Capabilities - ICBS 2024

Explore "educability" as a defining human capability, synthesizing learning from experience and others to explain humanity's achievements and guide future technology development.

• YouTube
• 1 hour 3 minutes
• On-Demand
• Free Video

Simons Institute

Agnostic Proper Learning of Monotone Functions: Beyond the Black-Box Correction Barrier

Explore efficient algorithms for agnostic, proper learning of monotone Boolean functions, overcoming previous limitations and achieving near-optimal runtime complexity.

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

Simons Institute

Testing Noise Assumptions in Machine Learning Algorithms - Theory and Implementation

Delve into algorithmic methods for testing noise assumptions in machine learning datasets, focusing on halfspace learning with Massart noise and the implications for computational learning theory.

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

UofU Data Science

Mistake Bound Learning and Halving Bound Applications - Lecture 8a

Delve into mistake bound learning theory through practical examples and applications of the Halving bound in machine learning algorithms.

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

UofU Data Science

Learnability Results for Consistent Learners - Lecture 13

Delve into computational learning theory, exploring Occam's razor applications and key learnability principles for consistent learners through theoretical frameworks and practical insights.

• YouTube
• 1 hour 19 minutes
• On-Demand
• Free Video

UofU Data Science

Occam's Razor for Consistent Learners in PAC Learning - Lecture 12

Explore the theoretical foundations of PAC learning and understand how Occam's razor principles apply to consistent learners in machine learning theory.

• YouTube
• 1 hour 18 minutes
• On-Demand
• Free Video

UofU Data Science

VC Dimensions (Continued) - Lecture 16

Dive into computational learning theory and VC dimensions in this concluding lecture on the topic.

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

UofU Data Science

Machine Learning: Positive and Negative Learnability Results - Lecture 16

Explore key theoretical foundations of machine learning through positive and negative learnability results, enhancing your understanding of learning theory fundamentals.

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

Kolmogorov-Seminar

PAC Learning: From Finite Families to CNF Formulas - Lecture on March 20, 2023

Dive into PAC learning concepts, exploring finite families, conjunctions, k-CNFs, and NP-completeness in proper learning for 2-term CNF through advanced computational complexity theory.

• YouTube
• 2 hours 1 minute
• On-Demand
• Free Video