From 9191fbefb8c658ffc437685fc638860d46f944ff Mon Sep 17 00:00:00 2001 From: lcawl Date: Tue, 14 Aug 2018 15:45:44 -0700 Subject: [PATCH] [DOCS] Adds machine learning 6.4.0 highlights --- .../release-notes/highlights-6.4.0.asciidoc | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/docs/reference/release-notes/highlights-6.4.0.asciidoc b/docs/reference/release-notes/highlights-6.4.0.asciidoc index dc04ffa166cbb..71eefcb28a44a 100644 --- a/docs/reference/release-notes/highlights-6.4.0.asciidoc +++ b/docs/reference/release-notes/highlights-6.4.0.asciidoc @@ -15,6 +15,22 @@ See also <>. * Korean analysis tools - A new plugin has been added which provides analysis tools for the Korean language. The new `nori` analyzer can be used to analyze Korean text "out of the box" and custom analyzers can use a tokenizer, part of speech token filter and a Hanja reading form token filter. For more information, see {plugins}/analysis-nori.html[Nori Plugin]. * Add multiplexing token filter - This new token filter allows you to run tokens through multiple different tokenfilters and stack the results. For example, you can now easily index the original form of a token, its lowercase form and a stemmed form all at the same position, allowing you to search for stemmed and unstemmed tokens in the same field. For more information, see <>. +[float] +=== Machine learning + +* Improve your machine learning results with custom rules. If you want to fine +tune your machine learning results (for example, to skip anomalies related to +certain servers), you can now create custom rules in {kib} and by using {ml} APIs. +Custom rules instruct anomaly detectors to change their behavior based on +domain-specific knowledge that you provide. See +{stack-ov}/ml-configuring-detector-custom-rules.html[Customizing detectors with custom rules] +* The {ml} analytics can now detect specific change points in a time series, +such as step changes, linear scaling, and time shifts (for example, related to +daylight savings). There is also a new probability model that can predict when +step changes might occur. As a result, the {ml} results are more robust and can +make more accurate predictions when these types of changes are present in your +data. + [float] === Mappings @@ -41,3 +57,4 @@ changes ranges include https://github.com/elastic/elasticsearch/pulls?q=is%3Aclo Specifically we want to highlight the https://github.com/elastic/elasticsearch/pull/30414[added support for AWS session tokens] to both the EC2 discovery plugin and the S3 repository plugins. This allows Elasticsearch to use AWS devices protected by multi factor authentication. +