rename mse into square_error after dev branch update.

05.recommender_system/README.cn.md

@@ -297,7 +297,7 @@ inference = paddle.layer.cos_sim(a=usr_combined_features, b=mov_combined_feature
 
 
 ```python
-cost = paddle.layer.mse_cost(
+cost = paddle.layer.square_error_cost(
         input=inference,
         label=paddle.layer.data(
             name='score', type=paddle.data_type.dense_vector(1)))
@@ -316,7 +316,7 @@ 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 [__mse_cost_0__]
+    [INFO 2017-03-06 17:12:13,287 networks.py:1478] The output order is [__square_error_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。
@@ -340,7 +340,7 @@ 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 [__mse_cost_0__]
+    [INFO 2017-03-06 17:12:13,379 networks.py:1478] The output order is [__square_error_cost_0__]
 
 
 ### 训练

05.recommender_system/README.md

@@ -275,7 +275,7 @@ 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.mse_cost(
+cost = paddle.layer.square_error_cost(
         input=inference,
         label=paddle.layer.data(
         name='score', type=paddle.data_type.dense_vector(1)))
@@ -303,7 +303,7 @@ 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 [__mse_cost_0__]
+[INFO 2017-03-06 17:12:13,379 networks.py:1478] The output order is [__square_error_cost_0__]
 ```
 
 ### Training

05.recommender_system/index.cn.html

@@ -339,7 +339,7 @@ inference = paddle.layer.cos_sim(a=usr_combined_features, b=mov_combined_feature
 
 
 ```python
-cost = paddle.layer.mse_cost(
+cost = paddle.layer.square_error_cost(
         input=inference,
         label=paddle.layer.data(
             name='score', type=paddle.data_type.dense_vector(1)))
@@ -358,7 +358,7 @@ 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 [__mse_cost_0__]
+    [INFO 2017-03-06 17:12:13,287 networks.py:1478] The output order is [__square_error_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。
@@ -382,7 +382,7 @@ 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 [__mse_cost_0__]
+    [INFO 2017-03-06 17:12:13,379 networks.py:1478] The output order is [__square_error_cost_0__]
 
 
 ### 训练

05.recommender_system/index.html

@@ -317,7 +317,7 @@ 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.mse_cost(
+cost = paddle.layer.square_error_cost(
         input=inference,
         label=paddle.layer.data(
         name='score', type=paddle.data_type.dense_vector(1)))
@@ -345,7 +345,7 @@ 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 [__mse_cost_0__]
+[INFO 2017-03-06 17:12:13,379 networks.py:1478] The output order is [__square_error_cost_0__]
 ```
 
 ### Training

05.recommender_system/train.py

@@ -72,7 +72,7 @@ def main():
     mov_combined_features = get_mov_combined_features()
     inference = paddle.layer.cos_sim(
         a=usr_combined_features, b=mov_combined_features, size=1, scale=5)
-    cost = paddle.layer.mse_cost(
+    cost = paddle.layer.square_error_cost(
         input=inference,
         label=paddle.layer.data(
             name='score', type=paddle.data_type.dense_vector(1)))