diff --git a/sklearn/neural_network/multilayer_perceptron.py b/sklearn/neural_network/multilayer_perceptron.py
index de559dc67e18f..19bd4ab5cd0bc 100644
--- a/sklearn/neural_network/multilayer_perceptron.py
+++ b/sklearn/neural_network/multilayer_perceptron.py
@@ -460,7 +460,7 @@ def _fit_lbfgs(self, X, y, activations, deltas, coef_grads,
         optimal_parameters, self.loss_, d = fmin_l_bfgs_b(
             x0=packed_coef_inter,
             func=self._loss_grad_lbfgs,
-            maxfun=self.max_iter,
+            maxiter=self.max_iter,
             iprint=iprint,
             pgtol=self.tol,
             args=(X, y, activations, deltas, coef_grads, intercept_grads))
diff --git a/sklearn/neural_network/tests/test_mlp.py b/sklearn/neural_network/tests/test_mlp.py
index b0d5ab587a087..4b1909606b4ac 100644
--- a/sklearn/neural_network/tests/test_mlp.py
+++ b/sklearn/neural_network/tests/test_mlp.py
@@ -633,3 +633,16 @@ def test_n_iter_no_change_inf():
 
     # validate _update_no_improvement_count() was always triggered
     assert_equal(clf._no_improvement_count, clf.n_iter_ - 1)
+
+
+@ignore_warnings(category=ConvergenceWarning)
+def test_lbfgs_max_iter():
+    # test n_iter_no_change using binary data set
+    # the fitting process should go to max_iter iterations
+    X = X_digits_binary[:100]
+    y = y_digits_binary[:100]
+
+    max_iter = 3000
+    clf = MLPClassifier(max_iter=max_iter, solver='lbfgs')
+    clf.fit(X, y)
+    assert clf.n_iter_ == max_iter