diff --git a/CODEOWNERS b/CODEOWNERS
index afa98df95..37e8fac91 100644
--- a/CODEOWNERS
+++ b/CODEOWNERS
@@ -33,7 +33,7 @@ keras_contrib/layers/normalization/groupnormalization.py @titu1994
 keras_contrib/layers/capsule.py @SriRangaTarun
 
 # losses
-
+keras-contrib/keras_contrib/losses/euclidean_distance_loss.py @RoadToML
 
 # metrics
 
diff --git a/contrib_docs/pydocmd.yml b/contrib_docs/pydocmd.yml
index eca7ba534..ffc02d716 100644
--- a/contrib_docs/pydocmd.yml
+++ b/contrib_docs/pydocmd.yml
@@ -23,6 +23,7 @@ generate:
         - keras_contrib.losses.jaccard_distance
         - keras_contrib.losses.crf_loss
         - keras_contrib.losses.crf_nll
+        - keras_contrib.losses.euclidean_distance_loss
 - optimizers.md:
     - keras_contrib.optimizers:
         - keras_contrib.optimizers.FTML
diff --git a/keras_contrib/losses/euclidean_distance_loss.py b/keras_contrib/losses/euclidean_distance_loss.py
new file mode 100644
index 000000000..2d9acfe9f
--- /dev/null
+++ b/keras_contrib/losses/euclidean_distance_loss.py
@@ -0,0 +1,15 @@
+import keras.backend as K
+
+
+def euclidean_distance_loss(y_true, y_pred):
+    """
+    The Euclidean distance between two points in Euclidean space.
+
+    # Arguments
+        y_true: tensor with true targets.
+        y_pred: tensor with predicted targets.
+
+    # Returns
+        float type Euclidean distance between two data points.
+    """
+    return K.sqrt(K.sum(K.square(y_pred - y_true), axis=-1))