MLOps at Acerta - Automating the Machine Learning Lifecycle for Manufacturing
Automate the machine learning lifecycle for manufacturing, enhancing efficiency, scalability, and reproducibility. Learn to build a robust MLOps platform for production-grade systems.
Machine Learning Monitoring in Production - Lessons Learned from 30+ Use Cases
Discover practical strategies for effective machine learning monitoring in production, drawing insights from over 30 real-world use cases.
How Not to Let Your Data and Model Drift Away Silently
Discover strategies to prevent data and model drift, ensuring ML models maintain performance and value over time in production environments.
Introduction to Drifter ML: A Testing Framework for Machine Learning Models
Explore Drifter-ML, a testing framework ensuring ML models meet training assumptions. Learn motivations and practical examples for model testing.
Building Production ML Monitoring from Scratch - Live Coding Session
Build a cloud-native ML monitoring stack using open-source tools. Create a live web dashboard to measure model drift, feature statistics, and performance metrics in production, with Python-based custom metrics integration.
How to Detect Silent Failures in ML Models
Learn techniques to detect and address silent failures in machine learning models, including data drift detection, performance estimation, and monitoring strategies, without relying on ground truth data.
Building and Maintaining High-Performance AI
Learn strategies for developing and maintaining high-performance AI models, including testing methods, drift detection, and systematic debugging. Gain insights on model monitoring and iteration for optimal performance.
The Missing Piece of MLOps: Observability in Machine Learning Applications
Explore ML observability's role in MLOps, learn to prepare for it, and discover how it showcases business value and recognizes data scientists' work.
One Analysis a Day Keeps Anomalies Away - Detecting and Analyzing Data Anomalies
Explore Python techniques for data observability, anomaly detection, and root cause analysis in multivariate time series. Learn to distinguish anomalies from data drift and turn insights into opportunities.
Efficient MLOps: Developing and Deploying ML Models with Databricks
Explore efficient MLOps framework design for ML model development and deployment, covering environment management, CI/CD pipelines, and tools like Unity Catalog and MLflow for model monitoring and progression.
The Next Frontier - Observability in ML Systems
Explore the frontier of ML systems observability, covering key components, challenges, and future trends in various domains including LLMs and computer vision.
Monitoring ML Models - Full Stack Deep Learning - Spring 2021
Learn techniques for monitoring ML models in production, including detecting data drift, measuring changes, and using tools to maintain model health and performance over time.
Dataset Management for Computer Vision - Important Component to Delivering Computer Vision Solutions
Explore dataset management's crucial role in computer vision solutions. Learn to align business goals, express assumptions, and maintain datasets for successful real-world implementations.
Testing ML Models in Production - Detecting Data and Concept Drift
Explore robust ML model testing in production using MLflow, SciPy, and statsmodels. Learn key statistical tests, metrics for drift detection, and gain practical insights for maintaining model effectiveness.
Prometheus in the MLOps Lifecycle
Explore Prometheus for monitoring ML deployments, addressing data drift, concept drift, and model metrics. Learn to enhance existing setups and integrate with Flyte, Seldon Core, or FastAPI.
Securing ML Workloads with Kubeflow and MLOps - Pwned By Statistics
Learn to secure machine learning workloads using Kubeflow and MLOps. Explore techniques like model extraction, hidden data attacks, and leakage detection to protect your ML pipelines and models.
Avoid the Top 5 Web Data Pitfalls When Developing AI Models
Explore strategies to overcome common challenges in AI model development, including data bias, insufficient variety, overfitting, poor quality, and data drift. Learn to create more robust and effective AI models.
Ekya - Continuous Learning of Video Analytics Models on Edge Compute Servers
Continuous learning for edge video analytics models, addressing data drift and balancing inference-retraining tradeoffs. Ekya optimizes resource allocation for improved accuracy with fewer GPU resources.
Observability in the MLOps Lifecycle with Prometheus
Explore MLOps monitoring with Prometheus, covering ML deployment challenges, data drift, and model metrics. Learn to enhance existing systems and integrate with tools like Flyte, Seldon Core, and FastAPI.
Monitoring Unstructured Data - Lightning Session
Explore ML observability for unstructured data with Arize. Learn about embeddings, monitoring challenges, and solutions through expert insights and a product demo.
Federated Learning for Healthcare: Private and Personal Clinical Modeling
Explore federated learning's application in healthcare, focusing on training machine learning models across distributed clinical datasets without compromising sensitive data privacy and security.