Amazon SageMaker Canvas now supports NLP and CV use cases
Amazon SageMaker Canvas now provides ready-to-use models so you can generate insights from thousands of documents, images, and lines of text in minutes. Additionally, you can now create custom models to address natural language processing (NLP) and computer vision (CV) use cases. SageMaker Canvas is a visual interface that enables business analysts to generate accurate machine learning (ML) predictions on their own—without requiring any ML experience or having to write a single line of code.
Amazon SageMaker Canvas now provides ready-to-use models so you can generate insights from thousands of documents, images, and lines of text in minutes. Additionally, you can now create custom models to address natural language processing (NLP) and computer vision (CV) use cases. SageMaker Canvas is a visual interface that enables business analysts to generate accurate machine learning (ML) predictions on their own—without requiring any ML experience or having to write a single line of code.
Business analysts are increasingly looking to accelerate their ability to generate insights from a variety of data and respond to ad-hoc analysis requests from business stakeholders. The process is often manual, time-consuming, and error-prone. ML can help business analysts analyze and generate insights from large volumes of data, but creating ML models often requires deep technical expertise.
Starting today, you can now use SageMaker Canvas to access ready-to-use models or create custom models for specific image or text classification use cases. Ready-to-use models are powered by AWS AI services, including Amazon Rekognition, Amazon Textract, and Amazon Comprehend. To create a custom model, you can import, prepare, explore, and label data. You can then train a custom model and evaluate the model’s performance. For custom image classification models, you can use heat maps to gain visibility into the training data that is impacting the model’s performance. You can also correct the model predictions if incorrect, add the verified data back to the original training dataset, and re-train the model to iteratively improve the model’s performance. Finally, you can generate accurate predictions without writing a single line of code.
Ready-to-use models and custom models for NLP and CV use cases are now available in all AWS regions where SageMaker Canvas is supported. To learn more, refer to the AWS News Blog and SageMaker Canvas product documentation.