scikit-learn
diff --git a/‎sklearn/neural_network/multilayer_perceptron.py
Lines changed: 16 additions & 15 deletions b/‎sklearn/neural_network/multilayer_perceptron.py
Lines changed: 16 additions & 15 deletions
@@ -601,15 +601,16 @@ def _update_no_improvement_count(self, early_stopping, X_val, y_val):
                 self.best_loss_ = self.loss_curve_[-1]
 
     def fit(self, X, y):
-        """Fit the model to data matrix X and target y.
+        """Fit the model to data matrix X and target(s) y.
 
         Parameters
         ----------
-        X : {array-like, sparse matrix}, shape (n_samples, n_feature
8000
s)
+        X : array-like or sparse matrix, shape (n_samples, n_features)
             The input data.
 
-        y : array-like, shape (n_samples,)
-            The target values.
+        y : array-like, shape (n_samples,) or (n_samples, n_outputs)
+            The target values (class labels in classification, real numbers in
+            regression).
 
         Returns
         -------
@@ -818,17 +819,17 @@ class MLPClassifier(BaseMultilayerPerceptron, ClassifierMixin):
 
     Attributes
     ----------
-    `classes_` : array or list of array of shape (n_classes,)
+    classes_ : array or list of array of shape (n_classes,)
         Class labels for each output.
 
-    `loss_` : float
+    loss_ : float
         The current loss computed with the loss function.
 
-    `coefs_` : list, length n_layers - 1
+    coefs_ : list, length n_layers - 1
         The ith element in the list represents the weight matrix corresponding
         to layer i.
 
-    `intercepts_` : list, length n_layers - 1
+    intercepts_ : list, length n_layers - 1
         The ith element in the list represents the bias vector corresponding to
         layer i + 1.
 
@@ -838,10 +839,10 @@ class MLPClassifier(BaseMultilayerPerceptron, ClassifierMixin):
     n_layers_ : int
         Number of layers.
 
-    `n_outputs_` : int
+    n_outputs_ : int
         Number of outputs.
 
-    `out_activation_` : string
+    out_activation_ : string
         Name of the output activation function.
 
     Notes
@@ -1163,14 +1164,14 @@ class MLPRegressor(BaseMultilayerPerceptron, RegressorMixin):
 
     Attributes
     ----------
-    `loss_` : float
+    loss_ : float
         The current loss computed with the loss function.
 
-    `coefs_` : list, length n_layers - 1
+    coefs_ : list, length n_layers - 1
         The ith element in the list represents the weight matrix corresponding
         to layer i.
 
-    `intercepts_` : list, length n_layers - 1
+    intercepts_ : list, length n_layers - 1
         The ith element in the list represents the bias vector corresponding to
         layer i + 1.
 
@@ -1180,10 +1181,10 @@ class MLPRegressor(BaseMultilayerPerceptron, RegressorMixin):
     n_layers_ : int
         Number of layers.
 
-    `n_outputs_` : int
+    n_outputs_ : int
         Number of outputs.
 
-    `out_activation_` : string
+    out_activation_ : string
         Name of the output activation function.
 
     Notes