Spatial Modeling of Single-Cell Data Using Deep Learning
Explore deep learning approaches for spatial modeling of single-cell data, focusing on Hi-C reads imputation and transcriptomic data prediction through graph-based methodologies.
Information Retrieval in the Era of Large Language Models
Explore how large language models are transforming information retrieval systems, with focus on event detection, clinical data extraction, and social media analysis for epidemic prediction.
Epigenomics Data Analysis - A Tutorial
Master essential techniques for analyzing epigenomics data, including ChIP-Seq analysis, histone modification clustering, and transcriptome integration methods for genomic research.
Harnessing Computational Genomics for Predicting Viral Evolution
Discover cutting-edge computational methods for predicting viral evolution patterns, focusing on genomic analysis techniques and emerging variant detection through network-based approaches and mutational studies.
Promises and Pitfalls of Scaling in Population Genetic Simulations
Explore the complexities of population genetic simulations, focusing on scaling methodologies, their potential benefits, and inherent limitations in computational genomics research.
Variational Inference for Fun and Profit
Discover the fundamentals of variational inference in statistical analysis, exploring Bayesian techniques, SuSiE PCA methodology, and practical applications in computational genomics and regression modeling.
Deploying Large Language Models on Kubernetes Environments for Intelligent Applications
Master the deployment of Large Language Models on Kubernetes, enabling intelligent applications with chatbots for documentation interaction and operational tasks like anomaly detection.
Making RAG Work - Building Robust Retrieval Augmented Generation Systems
Dive into practical techniques for implementing robust RAG systems, exploring common pitfalls, optimization strategies, and design principles for production-ready LLM applications.
Web Extraction with Large Language Models - Lessons from Parsing Billions of Webpages
Discover cutting-edge techniques for web scraping and data extraction using Large Language Models, drawing from Pinterest's experience of parsing billions of webpages daily.
Building Reproducible ML Processes with an Open Source Stack
Discover how to build truly reproducible machine learning experiments by integrating MLFlow, Git, lakeFS, and infrastructure-as-code for consistent data, code, and environment management.
AI-Ready Data Infrastructure for Real-Time Sensor Data Analytics on the Edge
Explore practical strategies for building edge-based real-time sensor data analytics infrastructure, using race strategy analytics as a case study to demonstrate cross-industry applications.
How Knowledge Graphs Help Generative AI Models Answer Questions
Discover how Knowledge Graphs enhance RAG patterns in LLMs, improving accuracy and relationship mapping for more precise AI responses across finance and healthcare applications.
Building Arcane - A Retrieval-Augmented Generation System for Investment Policies
Discover how to build Arcane, a RAG system that revolutionizes policy retrieval in financial institutions, boosting productivity through AI-powered document search and information extraction.
Real-Time Event Streaming Patterns for AI-Native Applications
Explore how event streaming patterns power AI applications through real-time analytics, data enrichment, and stream processing for enhanced intelligence and reliable infrastructure.
Secure Numerical Computing is Hard: Lessons from 10 Years of Open Data Science and the Long Road Ahead
Explore key security challenges and lessons learned from a decade of open data science, focusing on enterprise adoption of ML/AI technologies and emerging threats in numerical computing.
Moving Data Platforms to Knowledge Platforms - From Data Architecture to Enterprise AI
Discover how knowledge platforms and graphs revolutionize enterprise AI by transforming traditional data architectures into dynamic, context-rich knowledge systems for enhanced data utilization.
Detecting Botnets via DNS Traffic Analysis Using Machine Learning
Discover advanced techniques for detecting botnet-infected devices through DNS traffic analysis, combining natural language processing and machine learning for enhanced network security monitoring.
Multimodal RAG with LangChain, VertexAI, Gemini Pro and Chroma
Aprende a construir aplicaciones RAG multimodales utilizando LangChain, VertexAI y Chroma para procesar eficientemente datos no estructurados como PDFs e imágenes.
Multimodal RAG with LlamaIndex, Google AI, Gemini Pro and Qdrant
Explore cómo crear aplicaciones RAG multimodales utilizando LlamaIndex, Google AI Studio SDK y Gemini Pro para extraer información estructurada de imágenes con Qdrant como vector store.
Data Contracts Are Good for AI
Discover how data contracts and the ODCS standard enhance AI development, focusing on Bitol's open-source tools for modern data engineering and contract enforcement.
Effective and Efficient: Learn from AGL's Delivery Process Backed by Data and Analytics
Explore AGL's automotive software delivery process through data analytics, understanding performance metrics and development practices for optimizing software production systems.