Theoretical Machine Learning Courses and Certifications

Institute for Advanced Study

Latent State Recovery in Reinforcement Learning - John Langford

Explore latent state recovery in reinforcement learning, covering core problems, alternative approaches, and state abstraction. Gain insights from John Langford's expertise in theoretical machine learning.

• YouTube
• 1 hour 11 minutes
• Self-Paced
• Free Video

Institute for Advanced Study

Learning Probability Distributions - What Can, What Can't Be Done - Shai Ben-David

Explore probability distribution learning, its possibilities and limitations. Shai Ben-David discusses density estimation, sample compression schemes, and challenges in statistical learning theory.

• YouTube
• 57 minutes
• Self-Paced
• Free Video

Institute for Advanced Study

Latent Stochastic Differential Equations for Irregularly-Sampled Time Series - David Duvenaud

Explore advanced techniques for analyzing irregularly-sampled time series data using latent stochastic differential equations, with applications in predictive modeling and continuous-time machine learning.

• YouTube
• 1 hour 5 minutes
• Self-Paced
• Free Video

Institute for Advanced Study

Your Brain on Energy-Based Models - Applying and Scaling EBMs to Problems

Explore energy-based models in machine learning, covering applications, scaling techniques, and their impact on classification, calibration, and robustness in AI systems.

• YouTube
• 45 minutes
• Self-Paced
• Free Video

Institute for Advanced Study

Understanding Deep Neural Networks - From Generalization to Interpretability

Explore deep neural networks, focusing on generalization and interpretability. Delve into graph convolutional networks, spectral filtering, and transferability. Examine fundamental questions and relevance mapping in machine learning.

• YouTube
• 1 hour 2 minutes
• Self-Paced
• Free Video

Simons Institute

Learning and Generalization in Over-parametrized Neural Networks - Going Beyond Kernels

Explore neural network learning and generalization beyond kernel methods, examining tangent kernels, learning algorithms, and complexity in over-parametrized networks.

• YouTube
• 50 minutes
• Self-Paced
• Free Video

Alan Turing Institute

Does Learning Require Memorization? A Short Tale About a Long Tail - Vitaly Feldman, Google Brain

Exploring the necessity of memorization in learning algorithms, this talk delves into privacy concerns, long-tail distributions, and the role of memorization in achieving optimal generalization error in deep learning.

• YouTube
• 45 minutes
• Self-Paced
• Free Video

International Centre for Theoretical Sciences

Inverse Problems under a Learned Generative Prior - Lecture 1

Explores inverse problems using generative priors, comparing to sparsity models. Covers theory, algorithms, and applications in compressive sensing and phase retrieval, with focus on deep learning approaches.

• YouTube
• 50 minutes
• Self-Paced
• Free Video

MITCBMM

Open Problems in the Theory of Deep Learning - Panel Discussion

Explore cutting-edge perspectives on deep learning theory with leading experts, addressing unresolved questions and future research directions in this dynamic field.

• YouTube
• 1 hour 2 minutes
• Self-Paced
• Free Video

Institut des Hautes Etudes Scientifiques (IHES)

A Spline Tour of Deep Learning: The Scattering Way

Explore deep learning's progress, challenges, and theoretical foundations. Gain insights into the geometric interpretation of deep networks and spline approximation, with a focus on Scattering Networks.

• YouTube
• 28 minutes
• Self-Paced
• Free Video

Google TechTalks

Representational Strengths and Limitations of Transformers

Explore the mathematical analysis of attention layers in transformers, comparing their representation power to other architectures and examining complexity parameters in various tasks.

• YouTube
• 58 minutes
• Self-Paced
• Free Video

Harvard CMSA

Topics in Deep Learning Theory - October 15, 2024

Dive into advanced theoretical concepts of deep learning through expert analysis of fundamental principles, mathematical frameworks, and cutting-edge research developments.

• YouTube
• 1 hour 13 minutes
• Self-Paced
• Free Video

Harvard CMSA

Topics in Deep Learning Theory - October 11, 2024

Explore advanced theoretical concepts and foundational principles of deep learning through expert-led discussions on neural network architecture, optimization, and mathematical frameworks.

• YouTube
• 1 hour 16 minutes
• Self-Paced
• Free Video

Harvard CMSA

Topics in Deep Learning Theory - September 19, 2024

Dive into advanced theoretical concepts of deep learning, exploring mathematical foundations and cutting-edge developments in neural network architecture and optimization techniques.

• YouTube
• 1 hour 16 minutes
• Self-Paced
• Free Video

Harvard CMSA

Topics in Deep Learning Theory - October 8, 2024

Dive into advanced theoretical concepts of deep learning through expert-led discussions on neural network architectures, optimization techniques, and mathematical foundations.

• YouTube
• 1 hour 15 minutes
• Self-Paced
• Free Video