AWS Machine Learning Blog

MARCH 1, 2023

Challenges In this section, we discuss challenges around various data sources, data drift caused by internal or external events, and solution reusability. For example, Amazon Forecast supports related time series data like weather, prices, economic indicators, or promotions to reflect internal and external related events.

Automation 101

Automation ETL Data Drift ML 101

The MLOps Blog

JUNE 27, 2023

Can you see the complete model lineage with data/models/experiments used downstream? Amazon SageMaker Ground Truth SageMaker Ground Truth is a fully managed data labeling service designed to help you efficiently label and annotate your training data with high-quality annotations. Can you render audio/video?

Machine Learning 134

Machine Learning Metadata Data Scientist Data Quality 134

The MLOps Blog

MARCH 12, 2024

Monitoring Monitor model performance for data drift and model degradation, often using automated monitoring tools. Observability tools: Use platforms that offer comprehensive observability into LLM performance, including functional logs (prompt-completion pairs) and operational metrics (system health, usage statistics).

Prompt Engineering 52

Prompt Engineering Prompt Engineer Large Language Models LLM 52

AWS Machine Learning Blog

SEPTEMBER 21, 2023

This workflow will be foundational to our unstructured data-based machine learning applications as it will enable us to minimize human labeling effort, deliver strong model performance quickly, and adapt to data drift.” – Jon Nelson, Senior Manager of Data Science and Machine Learning at United Airlines.

Auto-complete 130

Auto-complete Machine Learning Computer Vision ML 130