PAC Learning in Machine Learning Theory - Lecture 13
Explore the fundamental concepts of PAC (Probably Approximately Correct) learning theory and its applications in theoretical machine learning frameworks.
Machine Learning: Occam's Razor and Consistent Learners - Lecture 14
Delve into the principles of Occam's razor and its application in consistent learning algorithms, exploring key theoretical foundations of machine learning complexity.
The VC Dimension in Machine Learning - Lecture 18
Delve into the fundamental concept of VC dimension in machine learning theory, exploring its relationship with shattering and its implications for learning algorithms.
Machine Learning: Understanding Hypothesis Spaces Through Shattering - Lecture 17
Delve into the concept of shattering and its application in analyzing infinite hypothesis spaces within machine learning theory and computational learning frameworks.
Agnostic Learning in Machine Learning - Lecture 16
Dive into computational learning theory and explore the fundamental concepts of agnostic learning in machine learning applications and theoretical frameworks.
Perceptron Mistake Bound Theorem in Machine Learning - Lecture 10
Dive into the mathematical foundations of Perceptron algorithms, exploring the theorem and proof behind mistake bounds in machine learning classification.
Machine Learning: Representations and Learning in Online Systems - Lecture 9
Explore how hypothesis representation choices impact online learning algorithms and their effectiveness in machine learning applications.
Languages with Decidable Learning: A Meta-theorem
Explore finite-aspect checkable languages and their role in decidable learning, connecting expression syntax tree evaluation to finite tree automata for new learning results.
On Learning Polynomial Recursive Programs
Explore P-finite automata, a generalization of weighted automata with polynomial transition weights. Learn about their polynomial-time learnability in Angluin's MAT exact learning model.
Leslie G. Valiant - Turing Award Lecture 2010
Explore computational learning theory, machine learning, and brain modeling with Leslie G. Valiant, 2010 ACM Turing Award winner, as he discusses his groundbreaking research and insights.
Learning of Neural Networks with Quantum Computers and Learning of Quantum States with Graphical Models
Explores quantum algorithms for neural network learning and quantum state learning using graphical models, showcasing advancements in computational efficiency and sample complexity for specific quantum states.
Smoothed Analysis for Learning Concepts with Low Intrinsic Dimension
Explore smoothed analysis in machine learning, focusing on low-dimensional concepts and their applications. Gain insights into new algorithms for agnostic learning and margin-based approaches.
A Perceptron Trio - Computational vs Statistical Gaps in Learning and Optimization
Explore perceptron algorithms in machine learning, focusing on computational and statistical aspects in optimization and learning theory.
New Directions in Property Testing
Explore recent advancements in property testing algorithms, including new problems and frameworks connected to machine learning theory and high-dimensional data analysis.
Online Learning and Mistake Bound Analysis - Lecture 6B
Explore online learning algorithms and performance quantification through mistake bound methodology, focusing on mistake-driven learning approaches.
Positive and Negative Learnability Results in Machine Learning - Lecture 15
Delve into fundamental learnability concepts in machine learning, exploring both positive and negative results that shape our understanding of learning algorithms and their limitations.
Characterizations of PAC Learnability
Explore key characterizations of PAC learnability in machine learning theory with insights from postdoctoral researcher Nataly Brukhim.
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.
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.
Learning Sparse Boolean Functions: Neural Networks Need a Hierarchical Degree Chain
Explore neural networks' hierarchical degree chain for learning sparse Boolean functions. Gain insights from EPFL expert E. Abbé.
Learning Low-Degree Functions on the Discrete Hypercube
Explore computational learning theory through random query models and polynomial inequalities, improving estimates for query complexity in reconstructing hypercube functions.