diff --git a/docs/en/ml/introduction.asciidoc b/docs/en/ml/introduction.asciidoc
index 31f6d9c4fc1..55d71ec7137 100644
--- a/docs/en/ml/introduction.asciidoc
+++ b/docs/en/ml/introduction.asciidoc
@@ -38,7 +38,7 @@ Jobs::
 Data feeds::
   Jobs can analyze either a batch of data from a data store or a stream of data
   in real-time. The latter involves data that is retrieved from {es} and is
-  referred to as a _data feed_.
+  referred to as a data feed.
 
 Detectors::
   Part of the configuration information associated with a job, detectors define
@@ -54,7 +54,12 @@ Buckets::
   bucket span, take into account the granularity at which you want to analyze,
   the frequency of the input data, and the frequency at which alerting is required.
 
-
+Machine learning nodes::
+  A {ml} node is a node that has `xpack.ml.enabled` and `node.ml` set to `true`,
+  which is the default behavior. If you set `node.ml` to `false`, the node can
+  service API requests but it cannot run jobs. If you want to use {xpack} {ml}
+  features, there must be at least one {ml} node in your cluster.
+  For more information about this setting, see <<ml-settings>>.
 
 
 
diff --git a/docs/en/settings/index.asciidoc b/docs/en/settings/index.asciidoc
index be2fb013092..5b36ae98b79 100644
--- a/docs/en/settings/index.asciidoc
+++ b/docs/en/settings/index.asciidoc
@@ -10,6 +10,7 @@ configuration files.
 * <<monitoring-settings, Monitoring Settings>>
 * <<notification-settings, Watcher Settings>>
 * <<reporting-settings, Reporting Settings>>
+* <<ml-settings, Machine Learning Settings>>
 --
 
 include::security-settings.asciidoc[]
@@ -17,4 +18,4 @@ include::monitoring-settings.asciidoc[]
 include::graph-settings.asciidoc[]
 include::notification-settings.asciidoc[]
 include::reporting-settings.asciidoc[]
-
+include::ml-settings.asciidoc[]
diff --git a/docs/en/settings/ml-settings.asciidoc b/docs/en/settings/ml-settings.asciidoc
new file mode 100644
index 00000000000..f1310f612f0
--- /dev/null
+++ b/docs/en/settings/ml-settings.asciidoc
@@ -0,0 +1,29 @@
+[[ml-settings]]
+== Machine Learning Settings
+You do not need to configure any settings to use {ml}.
+
+[float]
+[[general-ml-settings]]
+=== General Machine Learning Settings
+
+`xpack.ml.enabled`::
+Set to `true` (default) to enable {ml}. +
++
+If set to `false` in `elasticsearch.yml`, the {ml} APIs are disabled.
+You also cannot open jobs or start data feeds.
+If set to `false` in `kibana.yml`, the {ml} icon is not visible in Kibana. +
++
+TIP: If you want to use {ml} features in your cluster, you must enable {ml} on
+all master-eligible nodes. This is the default behavior.
+
+`node.ml`::
+Set to `true` (default) to identify the node as a _machine learning node_. +
++
+If set to `false` in `elasticsearch.yml`, the node cannot run jobs.
+If you want to run jobs, there must be at least one machine learning node
+in your cluster. +
++
+TIP: On dedicated coordinating nodes or dedicated master nodes, disable
+the `node.ml` role.
+
+//Eventually this node information should be added to https://www.elastic.co/guide/en/elasticsearch/reference/5.3/modules-node.html