Release history for the Splunk App for Data Science and Deep Learning

The Splunk App for Data Science and Deep Learning (DSDL) is formerly known as the Deep Learning Toolkit (DLTK). DSDL became a Splunk supported app on November 2, 2022. For the release notes of the latest DSDL version, see New features for the Splunk App for Data Science and Deep Learning.

Version 3.9.0

• New ECOD anomaly detection Example.
• New certificate handling options.
• Addition of interactive Splunk search bar in Jupyter Lab Notebooks.
• Addition of functionality to send data from containers to Splunk HEC.
• Bug fix for the SHAP dashboard.
• Added Ingress option for Kubernetes clusters.
• Release includes a refresh of all images.

Version 3.8.0

• New option for integration with Splunk Observability.
• Addition of benchmarks for different dataset sizes.
• Addition of Online learning anomaly detection algorithm.
• Addition of the Container Operations dashboard.
• Release includes an update of all images.
• Release includes other various bug fixes.

To learn more about changes to this DSDL app version, see Deep Learning Toolkit 3.7 and 3.8 - What's New.

Version 3.7.0

• Update DLTK to work with MLTK version 5.3.0 and backwards compatible for version 5.x.
• Add option for Custom SSL Certificate in Setup UI.
• Addition of Simple Example for Hidden Markov Models.
• Release includes other minor bug fixes.

To learn more about changes to this DSDL app version, see the Splunk blog post Deep Learning Toolkit 3.7 and 3.8 - What's New.

Version 3.6.0

• Release includes bug fixes, updates and performance improvements.
• Addition of the Operational Overview dashboard.
• New drill-down links on the Container Management dashboard.
• Addition of several new Examples:
  • Automated Machine Learning with auto-sklearn
  • Robust Random Cut Forest for anomaly detection
  • Time series decomposition for seasonality and trend (STL)
  • Sentiment Analysis with spaCy
• Image update to Golden Image CPU 3.6.