HUJI Machine Learning Club Courses

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
• On-Demand
• 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
• On-Demand
• 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
• On-Demand
• 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
• On-Demand
• 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
• On-Demand
• 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
• On-Demand
• 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
• On-Demand
• 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
• On-Demand
• 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
• On-Demand
• Free Video

Mean Estimation in High-Dimensional Binary Markov Gaussian Mixture Models

Delve into high-dimensional mean estimation in binary Markov Gaussian mixture models, exploring how memory in data affects estimation error and the interplay between sample size, dimension, and signal strength.

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

Local Glivenko-Cantelli: Estimating the Mean in Infinite Dimensions

Delve into advanced statistical theory exploring mean estimation in infinite dimensions, focusing on Local Glivenko-Cantelli bounds and maximal deviation analysis for Boolean cube distributions.

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

Adversarial Streaming: A Survey of Robust Algorithm Design

Explore the evolution of streaming algorithms from oblivious to adaptive settings, examining robust methods and limitations of CountSketch in adversarial scenarios. Learn key transformation techniques for creating resilient streaming solutions.

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

Benefits of Deep and Narrow Neural Networks for Approximation and Memorization

Explore groundbreaking research on neural networks' architecture, revealing why depth trumps width in function approximation and how deep, narrow networks can efficiently memorize data using minimal parameters.

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

Gauss-Legendre Features for Scalable Gaussian Process Regression

Discover how Gauss-Legendre features enable efficient scaling of Gaussian process regression through low-rank kernel matrix approximation, offering faster computation for large datasets with poly-logarithmic feature requirements.

• YouTube
• 1 hour 5 minutes
• On-Demand
• Free Video

Coresets and Decision Trees for Machine Learning Optimization

Discover how coresets can optimize decision tree algorithms, boost computation speed by 10x, and maintain accuracy in machine learning applications through geometric partitioning techniques.

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