TMLS 2019 - Machine Learning Presentation
Explore machine learning insights from industry experts Hoyoung Jang and Cheng Lin at TMLS 2019, gaining valuable knowledge and perspectives on cutting-edge ML applications.
TMLS2019
Explore machine learning applications in personalized recommendations at Netflix, focusing on innovative techniques and challenges in content discovery.
Proving the Impact: Using Synthetic Control to Evaluate Intervention Effectiveness
Explore Synthetic Control methodology for measuring intervention impact when A/B testing isn't feasible. Learn to construct "synthetic" units, estimate causal effects, and apply this innovative approach to real-world scenarios.
Unraveling the Web of Relationships: Understanding Graph Data
Explore graph theory basics, real-world applications, and the growing importance of graph databases in solving complex data challenges across industries.
Building Trusted AI Products - Workshop
Gain insights on building trustworthy AI products through exercises and resources from the People + AI Research team, focusing on user-centered design and calibrating trust in AI development.
Getting Started with Qdrant - Introduction to Vector Database and Similarity Search
Master vector similarity search using Qdrant to build semantic search and recommendation systems through hands-on practice with sample datasets and practical implementations.
Milvus 2.0 - Building the World's Most Advanced Open-Source Vector Database
Explore Milvus 2.0, an advanced open-source vector database. Learn its architecture, layers, and applications in ML pipelines, smart property search, product recommendations, and more.
Milvus Vector Database - Unlocking the Future of Open Source Vector Databases
Explore Milvus, a high-performance cloud-native vector database. Learn its history, architecture, unique features, and real-world applications in RAG, recommendation systems, and molecular search.
The Distributed Open Source Graph Database - NebulaGraph
Explore graph databases, their applications, and NebulaGraph's features in this informative talk. Learn about use cases like recommendation systems and fraud detection.
Vector Database Explained - What is Vector Database and How to Use It
Explore vector databases: storage, similarity comparison, and applications. Learn Euclidean Distance for feature similarity, see real-world uses, and follow a demo using Bollywood movie plots on Replit.
Using Postgres and OpenAI to Power Your AI Recommendation Engine - RailsConf 2024
Discover how to build an AI recommendation engine using Rails, Postgres, and OpenAI. Learn optimization techniques for handling AI data and scaling your system effectively.
Mutual Information-based Preference Disentangling and Transferring for Cross-Domain Recommendations
Explore mutual information-based techniques for disentangling and transferring user preferences across multiple non-overlapping domains in recommendation systems.
Building a Recommendation System for EPAM Systems
Discover how EPAM Systems builds and implements recommendation systems, exploring ML approaches, business goals, feature engineering, quality metrics, and monitoring strategies in production.
Under Pressure: Applying Machine Learning in Real-Time Systems
Explore real-time machine learning implementation strategies, from handling low latency requirements to building scalable systems for streaming scenarios in autonomous vehicles, healthcare, and fraud detection.
AI-Powered Transformation in Fashion E-Commerce - Leveraging Customer Segmentation and Personalization
Discover how AI-driven customer segmentation and personalized recommendations revolutionize fashion e-commerce, boosting sales and customer loyalty through data-driven strategies and innovative solutions.
Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits
Delve into stochastic combinatorial semi-bandits with a focus on risk-controlled online decision making, exploring algorithms for optimal subset selection while maintaining variance constraints.
Scaling Open Source ML: How Wolt Uses Kubernetes to Deliver Great Food to Millions
Discover how Wolt leverages Kubernetes and open-source frameworks to scale machine learning operations, addressing challenges in forecasting, recommendations, and delivery time predictions for millions of users.
The Power of Graph Learning - Richard M. Karp Distinguished Lecture
Explore graph learning's applications, methods, and theoretical foundations. Discover connections between graph learning and database theory for insights into expressive power potential.
Vector Similarity Search
Explore vector similarity search, its applications in deep learning, and how it revolutionizes search across text, multimedia, and recommendations. Learn from industry experts about implementation and future possibilities.
Recent Advances in Diversity Maximization in the Offline and Composable Coreset Models
Explore recent advancements in diversity maximization for data summarization and recommendation systems, focusing on offline and composable coreset models for handling massive datasets efficiently.
Build a Movie Recommendation System Using Machine Learning
Learn to create a movie recommendation system using machine learning techniques. Explore data-driven approaches to personalize film suggestions based on user preferences and viewing history.