HUJI Machine Learning Club Courses

Risk Management in AI Models - Confidence Estimation in Machine Learning Classifiers

Explore the principles of confidence estimation in machine learning classifiers, focusing on geometric properties of training data to predict model certainty and manage risk in AI decision-making systems.

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

Algorithmic Dependent Generalization Bounds

Delve into algorithmic-dependent generalization bounds in machine learning with Roi Livni, exploring how algorithms like Gradient Descent and SGD impact generalization beyond classical theories.

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

Provable Benefits of Complex Parameterizations for Structured State Space Models (Heb)

Explore the theoretical advantages of complex parameterizations in Structured State Space Models (SSMs) like S4 and Mamba, with mathematical proofs showing why complex SSMs outperform real ones in expressivity and efficiency.

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

Convergence of Policy Mirror Descent Beyond Compatible Function Approximation (Hebrew)

Explore Uri Sherman's research on Policy Mirror Descent convergence, introducing a variational gradient dominance condition that enables convergence for general policy classes without strong closure requirements.

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

Sample Compression and Topological Radon Theorem in Machine Learning

Explore the intersection of topology and machine learning through an examination of sample compression schemes and the Radon theorem's novel applications in theoretical ML problems.

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

The Elusive Role of High Dimensions in Modern Optimization and Generalization

Delve into the fascinating role of high-dimensionality in deep learning optimization, exploring how modern neural networks challenge traditional theoretical constraints and achieve unprecedented success.

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

Real-World AI: Risk and Robustness in Reinforcement Learning and Kalman Filtering

Explore real-world applications of AI through risk-aware reinforcement learning and robust Kalman filtering, focusing on practical challenges and solutions for handling uncertainties in AI systems.

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

Geometry-oriented Measures of Dependence in Statistical Analysis

Explore geometric approaches to measuring statistical dependence, examining axioms and algorithms for evaluating relationships between variables while comparing classical and modern dependence measures.

• YouTube
• 1 hour 1 minute
• Self-Paced
• Free Video

Optimal Prediction Using Expert Advice and Randomized Littlestone Dimension

Delve into optimal prediction strategies and online learning theory through exploration of expert advice systems and the randomized Littlestone dimension, focusing on practical applications in weather forecasting and image classification.

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

Efficiency in the Age of Large Scale Models - Designing and Optimizing Deep Learning Systems

Explore the challenges and solutions of large-scale AI models, from theoretical foundations to practical efficiency improvements, with insights on reducing computational costs while maintaining performance in modern machine learning.

• YouTube
• 1 hour 4 minutes
• Self-Paced
• Free Video

Towards Reverse Algorithmic Engineering of Neural Networks

Explore the algorithmic decision-making process of neural networks through NeuroSAT case study, examining how ML models learn and apply combinatorial features and confidence-based variable selection in SAT solving.

• YouTube
• 1 hour 3 minutes
• Self-Paced
• Free Video

Graph Neural Networks: Modeling Interactions Between Vertices Through Walk Index Analysis

Explore the theoretical foundations of Graph Neural Networks' ability to model vertex interactions, focusing on separation rank, walk index, and a novel edge sparsification algorithm for improved performance.

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

Manifold Denoising with Application to Electron Microscopy

Discover advanced manifold denoising techniques for electron microscopy image processing, focusing on Fourier-like basis construction and filtering methods to enhance two-dimensional image collections through mathematical analysis.

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

Implications of Implicit Bias in ReLU Networks - Understanding Generalization and Robustness

Explore the implications of implicit bias in ReLU networks, covering generalization in shallow networks, vulnerability to adversarial examples, and privacy concerns in neural network training parameters.

• YouTube
• 1 hour 3 minutes
• Self-Paced
• Free Video

Empirical Challenges to Theories of Deep Learning

Explore empirical challenges in deep learning theory, examining network representations, non-monotonic training patterns, and complex learning processes through cutting-edge research findings and real-world examples.

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