diff --git a/fit_a_line/README.en.ipynb b/fit_a_line/README.en.ipynb
index 110b3031026f1fd0d65cbb1b3a7d45c43c86ee7a..a819dc5d0db3f7aa639834722ad024c1f22f49dc 100644
--- a/fit_a_line/README.en.ipynb
+++ b/fit_a_line/README.en.ipynb
@@ -189,7 +189,7 @@
         "                                size=1,\n",
         "                                act=paddle.activation.Linear())\n",
         "y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1))\n",
-        "cost = paddle.layer.regression_cost(input=y_predict, label=y)\n"
+        "cost = paddle.layer.mse_cost(input=y_predict, label=y)\n"
       ],
       "outputs": [
         {
diff --git a/fit_a_line/README.en.md b/fit_a_line/README.en.md
index eeef844d24c4ceb25028d7ec85a5335f82d5c51d..67bff40b73d02b02e54a6e7d555b4fbe4984d23b 100644
--- a/fit_a_line/README.en.md
+++ b/fit_a_line/README.en.md
@@ -132,7 +132,7 @@ y_predict = paddle.layer.fc(input=x,
                                 size=1,
                                 act=paddle.activation.Linear())
 y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1))
-cost = paddle.layer.regression_cost(input=y_predict, label=y)
+cost = paddle.layer.mse_cost(input=y_predict, label=y)
 ```
 ### Create Parameters
 
diff --git a/fit_a_line/README.ipynb b/fit_a_line/README.ipynb
index c690570a8a4ef048f2e3460a4b095919bf041f60..07f15fa38f330f55c63926888b2d732c486b2079 100644
--- a/fit_a_line/README.ipynb
+++ b/fit_a_line/README.ipynb
@@ -183,7 +183,7 @@
         "                                size=1,\n",
         "                                act=paddle.activation.Linear())\n",
         "y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1))\n",
-        "cost = paddle.layer.regression_cost(input=y_predict, label=y)\n"
+        "cost = paddle.layer.mse_cost(input=y_predict, label=y)\n"
       ],
       "outputs": [
         {
diff --git a/fit_a_line/README.md b/fit_a_line/README.md
index 6ae43bcc591e51b9ff91c61f2c8ae7e6ff407c25..b4516851e7e106750740557ccfbf31c8f1e4f5d0 100644
--- a/fit_a_line/README.md
+++ b/fit_a_line/README.md
@@ -126,7 +126,7 @@ y_predict = paddle.layer.fc(input=x,
                                 size=1,
                                 act=paddle.activation.Linear())
 y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1))
-cost = paddle.layer.regression_cost(input=y_predict, label=y)
+cost = paddle.layer.mse_cost(input=y_predict, label=y)
 ```
 ### 创建参数
 
diff --git a/fit_a_line/index.en.html b/fit_a_line/index.en.html
index 22d6aeaa7da7ef9277ca59ac29f8b0e62ba78fa3..0c8fe2e9afc637fe889270d960bd5a1e234df9cf 100644
--- a/fit_a_line/index.en.html
+++ b/fit_a_line/index.en.html
@@ -174,7 +174,7 @@ y_predict = paddle.layer.fc(input=x,
                                 size=1,
                                 act=paddle.activation.Linear())
 y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1))
-cost = paddle.layer.regression_cost(input=y_predict, label=y)
+cost = paddle.layer.mse_cost(input=y_predict, label=y)
 ```
 ### Create Parameters
 
diff --git a/fit_a_line/index.html b/fit_a_line/index.html
index 495d8e39726651c4efb2ce96d3c5da265bcfb171..efa0cc70e3671fa049e75798ef73268a5feaca28 100644
--- a/fit_a_line/index.html
+++ b/fit_a_line/index.html
@@ -168,7 +168,7 @@ y_predict = paddle.layer.fc(input=x,
                                 size=1,
                                 act=paddle.activation.Linear())
 y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1))
-cost = paddle.layer.regression_cost(input=y_predict, label=y)
+cost = paddle.layer.mse_cost(input=y_predict, label=y)
 ```
 ### 创建参数
 
diff --git a/fit_a_line/train.py b/fit_a_line/train.py
index 6fae9e012e6153c6fc84a30ea72d82f2d9a80200..fc4d263eb73e5370fa5288abb2f1f11a1f0a22e0 100644
--- a/fit_a_line/train.py
+++ b/fit_a_line/train.py
@@ -10,7 +10,7 @@ def main():
     x = paddle.layer.data(name='x', type=paddle.data_type.dense_vector(13))
     y_predict = paddle.layer.fc(input=x, size=1, act=paddle.activation.Linear())
     y = paddle.layer.data(name='y', type=paddle.data_type.dense_vector(1))
-    cost = paddle.layer.regression_cost(input=y_predict, label=y)
+    cost = paddle.layer.mse_cost(input=y_predict, label=y)
 
     # create parameters
     parameters = paddle.parameters.create(cost)
diff --git a/recommender_system/README.en.ipynb b/recommender_system/README.en.ipynb
index 8c9addf7c8dcedc37f018f8621c98077e59fb3ff..2eb6ca909d12bc37e8f96cf5ff1ddaa8bf330697 100644
--- a/recommender_system/README.en.ipynb
+++ b/recommender_system/README.en.ipynb
@@ -449,7 +449,7 @@
       },
       "source": [
         "inference = paddle.layer.cos_sim(a=usr_combined_features, b=mov_combined_features, size=1, scale=5)\n",
-        "cost = paddle.layer.regression_cost(\n",
+        "cost = paddle.layer.mse_cost(\n",
         "        input=inference,\n",
         "        label=paddle.layer.data(\n",
         "        name='score', type=paddle.data_type.dense_vector(1)))\n"
@@ -536,7 +536,7 @@
         "\n",
         "```text\n",
         "[INFO 2017-03-06 17:12:13,378 networks.py:1472] The input order is [user_id, gender_id, age_id, job_id, movie_id, category_id, movie_title, score]\n",
-        "[INFO 2017-03-06 17:12:13,379 networks.py:1478] The output order is [__regression_cost_0__]\n",
+        "[INFO 2017-03-06 17:12:13,379 networks.py:1478] The output order is [__mse_cost_0__]\n",
         "```\n",
         "\n",
         "### Training\n",
diff --git a/recommender_system/README.en.md b/recommender_system/README.en.md
index 9a1b5571cee03b926ac02dcc1d0f3920281db7f7..ca596efc749f24c9c3a8c9d1ee1f8dd1696d0a8f 100644
--- a/recommender_system/README.en.md
+++ b/recommender_system/README.en.md
@@ -254,7 +254,7 @@ Finally, we can use cosine similarity to calculate the similarity between user c
 
 ```python
 inference = paddle.layer.cos_sim(a=usr_combined_features, b=mov_combined_features, size=1, scale=5)
-cost = paddle.layer.regression_cost(
+cost = paddle.layer.mse_cost(
         input=inference,
         label=paddle.layer.data(
         name='score', type=paddle.data_type.dense_vector(1)))
@@ -282,7 +282,7 @@ trainer = paddle.trainer.SGD(cost=cost, parameters=parameters,
 
 ```text
 [INFO 2017-03-06 17:12:13,378 networks.py:1472] The input order is [user_id, gender_id, age_id, job_id, movie_id, category_id, movie_title, score]
-[INFO 2017-03-06 17:12:13,379 networks.py:1478] The output order is [__regression_cost_0__]
+[INFO 2017-03-06 17:12:13,379 networks.py:1478] The output order is [__mse_cost_0__]
 ```
 
 ### Training
diff --git a/recommender_system/README.ipynb b/recommender_system/README.ipynb
index e6459c2ac70c4e011987d31f99fcf7f02a234bb1..df6835a5c837c6a2d44e6455bdd19b8b7e040ebc 100644
--- a/recommender_system/README.ipynb
+++ b/recommender_system/README.ipynb
@@ -479,7 +479,7 @@
         "editable": true
       },
       "source": [
-        "cost = paddle.layer.regression_cost(\n",
+        "cost = paddle.layer.mse_cost(\n",
         "        input=inference,\n",
         "        label=paddle.layer.data(\n",
         "            name='score', type=paddle.data_type.dense_vector(1)))\n"
@@ -535,7 +535,7 @@
       "source": [
         "\n",
         "    [INFO 2017-03-06 17:12:13,284 networks.py:1472] The input order is [user_id, gender_id, age_id, job_id, movie_id, category_id, movie_title, score]\n",
-        "    [INFO 2017-03-06 17:12:13,287 networks.py:1478] The output order is [__regression_cost_0__]\n",
+        "    [INFO 2017-03-06 17:12:13,287 networks.py:1478] The output order is [__mse_cost_0__]\n",
         "\n",
         "\n",
         "`parameters`是模型的所有参数集合。他是一个python的dict。我们可以查看到这个网络中的所有参数名称。因为之前定义模型的时候，我们没有指定参数名称，这里参数名称是自动生成的。当然，我们也可以指定每一个参数名称，方便日后维护。\n",
@@ -603,7 +603,7 @@
       "source": [
         "\n",
         "    [INFO 2017-03-06 17:12:13,378 networks.py:1472] The input order is [user_id, gender_id, age_id, job_id, movie_id, category_id, movie_title, score]\n",
-        "    [INFO 2017-03-06 17:12:13,379 networks.py:1478] The output order is [__regression_cost_0__]\n",
+        "    [INFO 2017-03-06 17:12:13,379 networks.py:1478] The output order is [__mse_cost_0__]\n",
         "\n",
         "\n",
         "### 训练\n",
diff --git a/recommender_system/README.md b/recommender_system/README.md
index 7ee55048784a8af070adb4efd94b0509a6d75638..94f072db7233681c53408e44a57dc93483c1cfe7 100644
--- a/recommender_system/README.md
+++ b/recommender_system/README.md
@@ -268,7 +268,7 @@ inference = paddle.layer.cos_sim(a=usr_combined_features, b=mov_combined_feature
 
 
 ```python
-cost = paddle.layer.regression_cost(
+cost = paddle.layer.mse_cost(
         input=inference,
         label=paddle.layer.data(
             name='score', type=paddle.data_type.dense_vector(1)))
@@ -287,7 +287,7 @@ parameters = paddle.parameters.create(cost)
 ```
 
     [INFO 2017-03-06 17:12:13,284 networks.py:1472] The input order is [user_id, gender_id, age_id, job_id, movie_id, category_id, movie_title, score]
-    [INFO 2017-03-06 17:12:13,287 networks.py:1478] The output order is [__regression_cost_0__]
+    [INFO 2017-03-06 17:12:13,287 networks.py:1478] The output order is [__mse_cost_0__]
 
 
 `parameters`是模型的所有参数集合。他是一个python的dict。我们可以查看到这个网络中的所有参数名称。因为之前定义模型的时候，我们没有指定参数名称，这里参数名称是自动生成的。当然，我们也可以指定每一个参数名称，方便日后维护。
@@ -311,7 +311,7 @@ trainer = paddle.trainer.SGD(cost=cost, parameters=parameters,
 ```
 
     [INFO 2017-03-06 17:12:13,378 networks.py:1472] The input order is [user_id, gender_id, age_id, job_id, movie_id, category_id, movie_title, score]
-    [INFO 2017-03-06 17:12:13,379 networks.py:1478] The output order is [__regression_cost_0__]
+    [INFO 2017-03-06 17:12:13,379 networks.py:1478] The output order is [__mse_cost_0__]
 
 
 ### 训练
diff --git a/recommender_system/index.en.html b/recommender_system/index.en.html
index 819ae07cec931028ed264007d9af97b99f7b5335..d406e742da8c63eaf7162c5d0c6b0f234576f076 100644
--- a/recommender_system/index.en.html
+++ b/recommender_system/index.en.html
@@ -296,7 +296,7 @@ Finally, we can use cosine similarity to calculate the similarity between user c
 
 ```python
 inference = paddle.layer.cos_sim(a=usr_combined_features, b=mov_combined_features, size=1, scale=5)
-cost = paddle.layer.regression_cost(
+cost = paddle.layer.mse_cost(
         input=inference,
         label=paddle.layer.data(
         name='score', type=paddle.data_type.dense_vector(1)))
@@ -324,7 +324,7 @@ trainer = paddle.trainer.SGD(cost=cost, parameters=parameters,
 
 ```text
 [INFO 2017-03-06 17:12:13,378 networks.py:1472] The input order is [user_id, gender_id, age_id, job_id, movie_id, category_id, movie_title, score]
-[INFO 2017-03-06 17:12:13,379 networks.py:1478] The output order is [__regression_cost_0__]
+[INFO 2017-03-06 17:12:13,379 networks.py:1478] The output order is [__mse_cost_0__]
 ```
 
 ### Training
diff --git a/recommender_system/index.html b/recommender_system/index.html
index 97df04a45fec4ada58c15074c30d08bd2b911bc0..491b1a6d52e4efa01838cb39531b6f01dd88349a 100644
--- a/recommender_system/index.html
+++ b/recommender_system/index.html
@@ -310,7 +310,7 @@ inference = paddle.layer.cos_sim(a=usr_combined_features, b=mov_combined_feature
 
 
 ```python
-cost = paddle.layer.regression_cost(
+cost = paddle.layer.mse_cost(
         input=inference,
         label=paddle.layer.data(
             name='score', type=paddle.data_type.dense_vector(1)))
@@ -329,7 +329,7 @@ parameters = paddle.parameters.create(cost)
 ```
 
     [INFO 2017-03-06 17:12:13,284 networks.py:1472] The input order is [user_id, gender_id, age_id, job_id, movie_id, category_id, movie_title, score]
-    [INFO 2017-03-06 17:12:13,287 networks.py:1478] The output order is [__regression_cost_0__]
+    [INFO 2017-03-06 17:12:13,287 networks.py:1478] The output order is [__mse_cost_0__]
 
 
 `parameters`是模型的所有参数集合。他是一个python的dict。我们可以查看到这个网络中的所有参数名称。因为之前定义模型的时候，我们没有指定参数名称，这里参数名称是自动生成的。当然，我们也可以指定每一个参数名称，方便日后维护。
@@ -353,7 +353,7 @@ trainer = paddle.trainer.SGD(cost=cost, parameters=parameters,
 ```
 
     [INFO 2017-03-06 17:12:13,378 networks.py:1472] The input order is [user_id, gender_id, age_id, job_id, movie_id, category_id, movie_title, score]
-    [INFO 2017-03-06 17:12:13,379 networks.py:1478] The output order is [__regression_cost_0__]
+    [INFO 2017-03-06 17:12:13,379 networks.py:1478] The output order is [__mse_cost_0__]
 
 
 ### 训练
diff --git a/recommender_system/train.py b/recommender_system/train.py
index 62af9921feec5269e723ad6df8cbaaa9b0098bfe..e57599254cf2fb67309012db24febff28c66e6ed 100644
--- a/recommender_system/train.py
+++ b/recommender_system/train.py
@@ -61,7 +61,7 @@ def main():
 
     inference = paddle.layer.cos_sim(
         a=usr_combined_features, b=mov_combined_features, size=1, scale=5)
-    cost = paddle.layer.regression_cost(
+    cost = paddle.layer.mse_cost(
         input=inference,
         label=paddle.layer.data(
             name='score', type=paddle.data_type.dense_vector(1)))