Leverage FMs for business analysis at scale with Amazon SageMaker Canvas
Amazon SageMaker Canvas is a no-code tool to build ML models and generate machine learning (ML) predictions. As announced on October 5, customers can access and evaluate foundation models (FMs) from Amazon Bedrock and SageMaker JumpStart to generate and summarize content.
Amazon SageMaker Canvas is a no-code tool to build ML models and generate machine learning (ML) predictions. As announced on October 5, customers can access and evaluate foundation models (FMs) from Amazon Bedrock and SageMaker JumpStart to generate and summarize content.
Starting today, SageMaker Canvas expands these capabilities by making it easy for customers to adapt FMs to the patterns and nuances of a specific use case, enhancing its performance in terms of response quality, cost, and latency. For example, a financial analyst using SageMaker Canvas for forecasting analysis can now customize a base FM to generate summaries and recommendations for their reports with their own historical data.
To get started, customers upload a dataset, select a FM to tune, and SageMaker Canvas automatically creates and tunes the model. To help customers understand how well FM is performing on a given task, SageMaker Canvas displays performance metrics and allows customers to evaluate the model performance, so they can quickly understand if it fits their needs.
The new capabilities are available in all AWS regions where Amazon SageMaker Canvas, Amazon Bedrock, and Amazon SageMaker JumpStart are available today. To learn more, see the service documentation. Customers are charged based on the duration of training and the instance type used. For more information, see the Amazon SageMaker Pricing.