5 Pitfalls of Large Language Models in Production and How to Solve Them
Uncover challenges and strategies for managing Large Language Models in production. Learn to detect hallucinations, minimize risks, and optimize performance through continuous monitoring and AI observability.
Advanced SQL: Top Tips for Dealing with Real-World Data
Level up SQL skills with advanced techniques for messy data, window functions, and arrays to tackle real-world analytics challenges effectively.
Recommenders with Values: Developing Recommendation Engines in a Public Service Organization
Explore how BBC develops recommender systems aligned with public service values, addressing methodological and cultural challenges in content recommendation for diverse audiences.
Vector and Hybrid Search with Elasticsearch
Explore vector and hybrid search in Elasticsearch, covering classic search limitations, models, implementation, and integration with LLMs like ChatGPT for enhanced data retrieval.
Boost Your AI Projects with Unknown Data and Unknown Questions
Leverage data products, implement hybrid model deployment, and drive AI innovation by accessing unknown data with unknown questions for transformative advancements in your projects.
10x the Retrieval Quality of Vector Search - Enhancing Semantic Search and RAG Systems
Enhance vector search retrieval quality by encoding diverse information into single vectors, simplifying deployment and reducing post-processing needs.
MLOps and LLMOps: From Prompt to Observability - Lecture 1
Explore MLOps, AI observability, and LLMOps integration. Gain insights on implementing AI stores for enhanced management and governance of traditional and generative AI solutions across organizations.
Using Generative AI to Better Understand B2B Audiences - From Topic Modelling to Text Classification
Explore how Generative AI and LLMs enhance B2B audience understanding through topic modeling and text classification, improving data quality and audience interest analysis.
Building Intelligent Systems with MoE, Multimodality, and Crowd of Agents
Explore advanced AI systems using MoE, multimodality, and agent crowds. Learn techniques for building composite intelligent systems beyond single algorithms or models.
Can We Trust AI? Understanding and Training Virtual Assistants
Explore the importance of training virtual assistants, their potential pitfalls, and how to ensure AI reliability. Gain insights into effective AI interaction and learn to share your expertise with others.
Prompt Engineering - Chat with Confidence and Build AI Solutions
Discover best practices for prompt engineering, learn to chat confidently with LLMs, and explore AI solution examples in this introductory-level talk.
AI Demand Forecasting: Building a Scalable Machine Learning System for Thousands of Products
Explore ASOS's journey in building a scalable AI demand forecasting system, addressing challenges in ML modeling, data processing, and integration for improved stock management.
Building Profitable Models - Lessons from Marks and Spencer
Discover strategies for creating successful, profitable data models in supply chain and product lifecycle management, focusing on decision-making processes and forecast accuracy.
Fighting Skin Disease with AI: Leveraging Computer Vision for Skin Health Monitoring
Explore how AI and computer vision are revolutionizing skin health monitoring and empowering informed skincare decisions at scale.
Improving Complex RAG Systems and Achieving No-Regret, Lightning-Fast Deployment Iterations of LLMs
Enhance RAG systems and deploy LLM applications rapidly using AWS lambda aliases. Learn to evaluate production systems and overcome LLM limitations for safer, faster iterations.
Explaining Explainability: An Interdisciplinary Approach to Communicate Machine Learning Outcomes
Explore an interdisciplinary approach to communicating machine learning outcomes through explainable AI, combining technical interpretations with socio-technical perspectives for enhanced understanding.
Quantifying AI and What Comes Next - From Single Purpose to General Purpose
Explore the evolution of AI from single-purpose to general-purpose systems, drawing parallels with computing history and examining future implications through an entropic framework.
Networks and Recommendation Systems
Explore graph-based recommendation systems, their transparent implementation, and real-world applications in this technical deep dive for data science practitioners.
Leveraging Databricks for Advanced Geospatial Analysis
Explore advanced geospatial analysis using Databricks. Learn to process spatial data at scale, integrate GIS with big data analytics, and utilize the H3 index for efficient grid-based operations.
Turbocharge Your Machine Learning with Open Data
Explore the UK's open data landscape, its benefits, challenges, and applications to enhance machine learning projects and drive data-driven decision-making.
Accelerating Machine Learning Serving with Distributed Caches
Explore distributed caching strategies to optimize ML serving, reduce latency, and improve throughput in inference pipelines. Gain practical insights for implementation.