Google TechTalks Courses

The Data Minimization Principle in Machine Learning

Explore data minimization in machine learning, its challenges, and practical implementations. Examine optimization-based formalization and applications in high-stakes domains, revealing insights on privacy and efficiency.

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

Low Cost High Power Membership Inference Attacks

Explore robust, efficient membership inference attacks for machine learning privacy risk assessment. Learn to differentiate population and training data with minimal computational overhead.

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

Design is Testability - Understanding Software Testing Through Design Principles

Explore software design's impact on testability, linking design concepts to testing strategies for effective automated testing in continuous integration systems.

• YouTube
• 1 hour 12 minutes
• On-Demand
• Free Video

Limitations of Stochastic Selection with Pairwise Independent Priors

Explore stochastic selection problems with pairwise-independent priors and matroid constraints, examining limitations and optimal bounds for contention resolution and prophet inequalities.

• YouTube
• 1 hour 6 minutes
• On-Demand
• Free Video

NASA CARA - Air Traffic Control in Space

Explore NASA's orbital collision avoidance technology, its core algorithms, and importance in managing Earth-orbiting satellite traffic.

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

How Your Brain Processes Code - A Cognitive Perspective on Programming

Explore cognitive aspects of programming, understanding how the brain interprets code to enhance reading and learning new languages. Gain insights for improved code interaction.

• YouTube
• 1 hour 12 minutes
• On-Demand
• Free Video

Fixed-point Error Bounds for Mean-payoff Markov Decision Processes

Explore optimal transport techniques for deriving finite-time error bounds in reinforcement learning, focusing on mean-payoff Markov decision processes and stochastic fixed point iterations.

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

One Tree to Rule Them All: Polylogarithmic Universal Steiner Trees and Strong Sparse Partition Hierarchies

Explore polylogarithmic universal Steiner trees and strong sparse partition hierarchies. Learn about new constructions improving approximation guarantees and matching logarithmic lower bounds.

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

Understanding Oversmoothing in Graph Neural Networks (GNNs) - Insights from Two Theoretical Studies

Explore theoretical insights on oversmoothing in Graph Neural Networks, analyzing mechanisms, quantifying effects, and examining attention-based GNNs to enhance understanding and improve network performance.

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

Socially Responsible Software Development - Teaching Software Design Systematically

Explore socially responsible software development and its importance in education. Learn strategies for creating curricula that emphasize software as a message to future developers.

• YouTube
• 1 hour 2 minutes
• On-Demand
• Free Video

Understanding and Mitigating Copying in Diffusion Models

Explore frameworks for detecting replication in diffusion models, identify memorization factors, and learn techniques to reduce data replication during training and inference.

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

Efficient Training Image Extraction from Diffusion Models

Explore efficient techniques for extracting training images from diffusion models, addressing privacy concerns and copyright issues while uncovering insights into image duplication and template copying.

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

High-Dimensional Prediction for Sequential Decision Making

Explore efficient algorithms for online high-dimensional predictions, enabling no-regret guarantees, fairness, and uncertainty quantification in multiclass settings for improved decision-making.

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

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
• On-Demand
• Free Video

Differentially Private Sampling from Distributions - Google Algorithms Seminar

Explore private sampling from distributions, examining dataset size requirements for various distribution families and comparing private sampling to non-private learning in different parameter regimes.

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