The Missing Link- How AI Can Help Create a Safer Society and Better Businesses
Explore how AI and NLP can enhance crime-solving, improve business efficiency, and create safer societies by automating information linking and reducing investigative time.
Relationships Matter - Using Connected Data for Better Machine Learning
Explore graph-native ML for enhanced predictions using relationship data. Learn graph feature engineering, ML techniques, and hands-on applications to leverage network structures in your data science models.
Interpretable Machine Learning to Model Drug Perturbations in Single Cell Genomics
Explore interpretable machine learning for modeling drug effects on single-cell genomics. Learn about deep autoencoders, manifold identification, and predicting novel perturbations in cellular states.
Production Machine Learning Monitoring- Principles, Patterns and Techniques
Practical deep dive on production monitoring of machine learning models, covering standard techniques and advanced paradigms like concept drift, outlier detection, and explainability, with hands-on examples and architectural patterns.
Latency SLOs Done Right - Calculating and Setting Accurate Service Level Objectives
Explore accurate latency SLO calculation methods, including histogram-based approaches, to set mathematically correct quantiles and improve service level objectives for better monitoring and performance management.
Storm: Realtime Distributed Computing with Nathan Marz - ETE 2012
Explore Storm for real-time data processing, covering concepts, development, deployment, fault-tolerance, and practical applications in distributed computing environments.
Captcha Recognition Using PyTorch - Convolutional-RNN + CTC Loss
Learn to implement a Convolutional-RNN model for captcha recognition using PyTorch. Covers data preparation, model architecture, CTC loss, and training/inference processes.
Building a Petabyte-Scale Cybersecurity Data Mesh in Azure with Delta Lake - HSBC Case Study
Explore HSBC's innovative approach to building a petabyte-scale cybersecurity data mesh in Azure, leveraging Delta Lake to address unique challenges and empower analysts with a unified, scalable platform.
Data Lakehouse and Data Mesh - Two Sides of the Same Coin
Explore how Data Lakehouse and Data Mesh complement each other in modern data management, combining technological advancements with organizational strategies for effective analytics.
Introducing MLflow for End-to-End Machine Learning on Databricks
Learn to predict life expectancy using health data with MLflow. Covers data engineering, exploration, model tuning, and deployment on Databricks' unified analytics platform powered by Apache Spark.
Combining Machine Learning and MLflow with Lakehouse Architecture - Data Brew Episode 5
Explore how Quby leverages ML and MLflow with their lakehouse to extract value from IoT sensor data, moving from batch to real-time streaming for energy optimization and customer insights.
MATS Stack for Cross-System Orchestration of Machine Learning Pipelines
Explore the MATS stack for orchestrating ML pipelines across systems, featuring MLFlow, Airflow, Tensorflow, and Spark. Learn how Avast leverages this approach for efficient phishing detection and streamlined ML workflows.
Spark NLP - State-of-the-Art Natural Language Processing at Scale
Discover scalable NLP techniques using Apache Spark, covering core algorithms, BERT embeddings, and multi-lingual challenges. Learn to build efficient pipelines for various NLP tasks through practical demonstrations.
Photon Vectorized Execution Engine - Technical Deep Dive
Explore Photon's vectorized execution engine, learning about expression evaluation, compute kernels, runtime adaptivity, and vectorized operations for enhanced data processing efficiency.
Model Experiments Tracking and Registration Using MLflow on Databricks
Automate ML model experimentation and tracking using MLflow on Databricks. Learn to streamline data preparation, model development, and artifact management for efficient machine learning workflows.
ML Production Pipelines: Building and Deploying a Classification Model
Learn to build and deploy production-ready machine learning pipelines using Python, Databricks, and MLflow. Explore training and prediction workflows, model registration, and deployment options for both batch and on-demand processing.
MLflow at Company Scale - Scaling and Optimizing for High-Volume Machine Learning
Learn how Criteo scaled MLflow to handle massive data volumes, including horizontal scaling, monitoring, SSO integration, and hadoop cluster integration for data scientists.
Frequently Bought Together Recommendations Using Embeddings - Challenges and Solutions
Explore embedding-based "frequently bought together" recommendations for e-commerce, covering model training, productionization, metrics, and serving strategies. Learn practical tips for large-scale implementation.
Data Mesh in Practice - Beyond the Data Lake for Fashion E-Commerce
Explore Zalando's journey from centralized Data Lake to distributed Data Mesh architecture, emphasizing data ownership, quality, and accessibility through decentralized domain-focused approach and Data Products concept.
Implementing a GAN to Remove People from Images - Databricks Lightning Talk
Learn to implement a pix2pix GAN on Databricks for removing people from images, exploring the basics, idea, demo, and analysis of this innovative image editing technique.
Taking Machine Learning to Production with MLflow - New Features and Best Practices
Explore MLflow's latest features for productionizing machine learning, including model management, CI/CD, data schemas, and integration with PyTorch for seamless deployment and operation of ML applications.