The PI.EXCHANGE team are excited to provide to our users two new powerful capabilities added to The AI & Analytics Engine, dataset download and continuous learning.
The Engine now provides users with the capability to download their datasets in a different file formats including; CSV, Json Lines, or Parquet. With this feature, users can leverage The Engine to transform RAW datasets into their desired format, then download it for continued use in an external environment.
Users can trigger dataset download from:
Check out our Knowledge Hub for more information on dataset download.
Continuous learning provides users the capability to update the trained prediction model to take into account the additional available data. This is particularly useful for situations where additional data only becomes available with the passage of time, and updating already trained models with the additional data will help it make better predictions.
The concept of Continuous Learning touches the following sections within the AI & Analytics Engine:
Updating the existing dataset with additional available data
When enabled, the PROCESSED dataset will automatically be updated when the associated RAW dataset is updated by the user. And, trained model will automatically update through partial fitting or refitting to the latest updated version of the trained dataset, once available.
When enabled, newer instances of the same trained model will be automatically deployed to replace the existing deployment, and assigned to the same endpoint. This enables an easy update of deployments with the updated trained model while ensuring that the endpoint remains intact with minimal downtime.
Check out our Knowledge Hub for more information on continuous learning.