fix dead link for book (#803)

02.recognize_digits/README.cn.md

@@ -37,7 +37,7 @@ MNIST吸引了大量的科学家基于此数据集训练模型，1998年，LeCun
 
 - $Y$是输出：分类器的输出是10类数字（0-9），即$Y=\left ( y_0, y_1, \dots, y_9 \right )$，每一维$y_i$代表图片分类为第$i$类数字的概率。
 
-- $Label$是图片的真实标签：$Label=\left ( l_0, l_1, \dots, l_9 \right )$也是10维，但只有一维为1，其他都为0。例如某张图片上的数字为2，则它的标签为$(0,0,1,0, \dot, 0)$
+- $Label$是图片的真实标签：$Label=\left ( l_0, l_1, \dots, l_9 \right )$也是10维，但只有一维为1，其他都为0。例如某张图片上的数字为2，则它的标签为$(0,0,1,0, \dots, 0)$
 
 ### Softmax回归(Softmax Regression)
 
@@ -113,7 +113,7 @@ Softmax回归模型采用了最简单的两层神经网络，即只有输入层
 
 - 局部连接：每个神经元仅与输入神经元的一块区域连接，这块局部区域称作感受野（receptive field）。在图像卷积操作中，即神经元在空间维度（spatial dimension，即上图示例H和W所在的平面）是局部连接，但在深度上是全部连接。对于二维图像本身而言，也是局部像素关联较强。这种局部连接保证了学习后的过滤器能够对于局部的输入特征有最强的响应。局部连接的思想，也是受启发于生物学里面的视觉系统结构，视觉皮层的神经元就是局部接受信息的。
 
-- 权重共享：计算同一个深度切片的神经元时采用的滤波器是共享的。例如图4中计算$o[:,:,0]$的每个每个神经元的滤波器均相同，都为$W_0$，这样可以很大程度上减少参数。共享权重在一定程度上讲是有意义的，例如图片的底层边缘特征与特征在图中的具体位置无关。但是在一些场景中是无意的，比如输入的图片是人脸，眼睛和头发位于不同的位置，希望在不同的位置学到不同的特征 (参考[斯坦福大学公开课]( http://cs231n.github.io/convolutional-networks/))。请注意权重只是对于同一深度切片的神经元是共享的，在卷积层，通常采用多组卷积核提取不同特征，即对应不同深度切片的特征，不同深度切片的神经元权重是不共享。另外，偏重对同一深度切片的所有神经元都是共享的。
+- 权重共享：计算同一个深度切片的神经元时采用的滤波器是共享的。例如图5中计算$o[:,:,0]$的每个每个神经元的滤波器均相同，都为$W_0$，这样可以很大程度上减少参数。共享权重在一定程度上讲是有意义的，例如图片的底层边缘特征与特征在图中的具体位置无关。但是在一些场景中是无意的，比如输入的图片是人脸，眼睛和头发位于不同的位置，希望在不同的位置学到不同的特征 (参考[斯坦福大学公开课]( http://cs231n.github.io/convolutional-networks/))。请注意权重只是对于同一深度切片的神经元是共享的，在卷积层，通常采用多组卷积核提取不同特征，即对应不同深度切片的特征，不同深度切片的神经元权重是不共享。另外，偏重对同一深度切片的所有神经元都是共享的。
 
 通过介绍卷积计算过程及其特性，可以看出卷积是线性操作，并具有平移不变性（shift-invariant），平移不变性即在图像每个位置执行相同的操作。卷积层的局部连接和权重共享使得需要学习的参数大大减小，这样也有利于训练较大卷积神经网络。
 

02.recognize_digits/README.md

@@ -29,7 +29,7 @@ To train a classifier based on MNIST dataset, before the introduction of three b
 
 - $Y$ is the output: the output of the classifier is number (0-9), ie $Y=\left ( y_0, y_1, \dots, y_9 \right )$, and each dimension $y_i$ represents the probability of image classification as $i$th number.
 
-- $Label$ is the actual label of the picture: $Label=\left ( l_0, l_1, \dots, l_9 \right ) $ is also 10 dimensions, but only one dimension represents 1, and the rest is 0. For example, if the number on an image is 2, its label is $(0,0,1,0, \dot, 0)$
+- $Label$ is the actual label of the picture: $Label=\left ( l_0, l_1, \dots, l_9 \right ) $ is also 10 dimensions, but only one dimension represents 1, and the rest is 0. For example, if the number on an image is 2, its label is $(0,0,1,0, \dots, 0)$
 
 ### Softmax Regression
 
@@ -98,7 +98,7 @@ The convolutional kernel is a learnable parameter in the convolution operation.
 
 - Local connection: Each neuron is connected to only one region of the input neuron, which is called Receptive Field. In the image convolution operation, that is, the neurons are locally connected in the spatial dimension (the plane in which the above examples H and W are located), but are fully connected in depth. For the two-dimensional image itself, the local pixels are strongly related. This local connection ensures that the learned filter makes the strongest response to local input features. The idea of local connection is also inspired by the structure of visual system in biology. The neurons in the visual cortex receive information locally.
 
-- Weight sharing: The filters used to calculate neurons in the same deep slice are shared. For example, in Figure 4, the filter for each neuron calculated by $o[:,:,0]$ is the same, both are $W_0$, which can greatly reduce the parameters. The sharing weight is meaningful to a certain extent, for example, the bottom edge feature of the image is independent of the specific location of the feature in the graph. However, it is unintentional in some cases. For example, the input picture is a face, eyes and hair are in different positions. And to learn different features in different positions, please (refer to [Stanford University Open Class](http://cs231n.Github.io/convolutional-networks/)). Note that the weights are only shared for the neurons of the same depth slice. In the convolutional layer, multiple sets of convolutional kernels are usually used to extract different features, that is, the weights of neurons with different depth slices are not shared by the features with different depth slices. In addition, bias are shared by all neurons with the same depth.
+- Weight sharing: The filters used to calculate neurons in the same deep slice are shared. For example, in Figure 5, the filter for each neuron calculated by $o[:,:,0]$ is the same, both are $W_0$, which can greatly reduce the parameters. The sharing weight is meaningful to a certain extent, for example, the bottom edge feature of the image is independent of the specific location of the feature in the graph. However, it is unintentional in some cases. For example, the input picture is a face, eyes and hair are in different positions. And to learn different features in different positions, please (refer to [Stanford University Open Class](http://cs231n.Github.io/convolutional-networks/)). Note that the weights are only shared for the neurons of the same depth slice. In the convolutional layer, multiple sets of convolutional kernels are usually used to extract different features, that is, the weights of neurons with different depth slices are not shared by the features with different depth slices. In addition, bias are shared by all neurons with the same depth.
 
 By introducing the calculation process of convolution and its features, convolution could be seen as a linear operation with shift-invariant, which is the same operation performed at each position of the image. The local connection and weight sharing of the convolutional layer greatly reduce the parameters that need to be learned, which helps with training larger convolutional neural networks.
 

02.recognize_digits/index.cn.html

@@ -79,7 +79,7 @@ MNIST吸引了大量的科学家基于此数据集训练模型，1998年，LeCun
 
 - $Y$是输出：分类器的输出是10类数字（0-9），即$Y=\left ( y_0, y_1, \dots, y_9 \right )$，每一维$y_i$代表图片分类为第$i$类数字的概率。
 
-- $Label$是图片的真实标签：$Label=\left ( l_0, l_1, \dots, l_9 \right )$也是10维，但只有一维为1，其他都为0。例如某张图片上的数字为2，则它的标签为$(0,0,1,0, \dot, 0)$
+- $Label$是图片的真实标签：$Label=\left ( l_0, l_1, \dots, l_9 \right )$也是10维，但只有一维为1，其他都为0。例如某张图片上的数字为2，则它的标签为$(0,0,1,0, \dots, 0)$
 
 ### Softmax回归(Softmax Regression)
 
@@ -155,7 +155,7 @@ Softmax回归模型采用了最简单的两层神经网络，即只有输入层
 
 - 局部连接：每个神经元仅与输入神经元的一块区域连接，这块局部区域称作感受野（receptive field）。在图像卷积操作中，即神经元在空间维度（spatial dimension，即上图示例H和W所在的平面）是局部连接，但在深度上是全部连接。对于二维图像本身而言，也是局部像素关联较强。这种局部连接保证了学习后的过滤器能够对于局部的输入特征有最强的响应。局部连接的思想，也是受启发于生物学里面的视觉系统结构，视觉皮层的神经元就是局部接受信息的。
 
-- 权重共享：计算同一个深度切片的神经元时采用的滤波器是共享的。例如图4中计算$o[:,:,0]$的每个每个神经元的滤波器均相同，都为$W_0$，这样可以很大程度上减少参数。共享权重在一定程度上讲是有意义的，例如图片的底层边缘特征与特征在图中的具体位置无关。但是在一些场景中是无意的，比如输入的图片是人脸，眼睛和头发位于不同的位置，希望在不同的位置学到不同的特征 (参考[斯坦福大学公开课]( http://cs231n.github.io/convolutional-networks/))。请注意权重只是对于同一深度切片的神经元是共享的，在卷积层，通常采用多组卷积核提取不同特征，即对应不同深度切片的特征，不同深度切片的神经元权重是不共享。另外，偏重对同一深度切片的所有神经元都是共享的。
+- 权重共享：计算同一个深度切片的神经元时采用的滤波器是共享的。例如图5中计算$o[:,:,0]$的每个每个神经元的滤波器均相同，都为$W_0$，这样可以很大程度上减少参数。共享权重在一定程度上讲是有意义的，例如图片的底层边缘特征与特征在图中的具体位置无关。但是在一些场景中是无意的，比如输入的图片是人脸，眼睛和头发位于不同的位置，希望在不同的位置学到不同的特征 (参考[斯坦福大学公开课]( http://cs231n.github.io/convolutional-networks/))。请注意权重只是对于同一深度切片的神经元是共享的，在卷积层，通常采用多组卷积核提取不同特征，即对应不同深度切片的特征，不同深度切片的神经元权重是不共享。另外，偏重对同一深度切片的所有神经元都是共享的。
 
 通过介绍卷积计算过程及其特性，可以看出卷积是线性操作，并具有平移不变性（shift-invariant），平移不变性即在图像每个位置执行相同的操作。卷积层的局部连接和权重共享使得需要学习的参数大大减小，这样也有利于训练较大卷积神经网络。
 

02.recognize_digits/index.html

@@ -71,7 +71,7 @@ To train a classifier based on MNIST dataset, before the introduction of three b
 
 - $Y$ is the output: the output of the classifier is number (0-9), ie $Y=\left ( y_0, y_1, \dots, y_9 \right )$, and each dimension $y_i$ represents the probability of image classification as $i$th number.
 
-- $Label$ is the actual label of the picture: $Label=\left ( l_0, l_1, \dots, l_9 \right ) $ is also 10 dimensions, but only one dimension represents 1, and the rest is 0. For example, if the number on an image is 2, its label is $(0,0,1,0, \dot, 0)$
+- $Label$ is the actual label of the picture: $Label=\left ( l_0, l_1, \dots, l_9 \right ) $ is also 10 dimensions, but only one dimension represents 1, and the rest is 0. For example, if the number on an image is 2, its label is $(0,0,1,0, \dots, 0)$
 
 ### Softmax Regression
 
@@ -140,7 +140,7 @@ The convolutional kernel is a learnable parameter in the convolution operation.
 
 - Local connection: Each neuron is connected to only one region of the input neuron, which is called Receptive Field. In the image convolution operation, that is, the neurons are locally connected in the spatial dimension (the plane in which the above examples H and W are located), but are fully connected in depth. For the two-dimensional image itself, the local pixels are strongly related. This local connection ensures that the learned filter makes the strongest response to local input features. The idea of local connection is also inspired by the structure of visual system in biology. The neurons in the visual cortex receive information locally.
 
-- Weight sharing: The filters used to calculate neurons in the same deep slice are shared. For example, in Figure 4, the filter for each neuron calculated by $o[:,:,0]$ is the same, both are $W_0$, which can greatly reduce the parameters. The sharing weight is meaningful to a certain extent, for example, the bottom edge feature of the image is independent of the specific location of the feature in the graph. However, it is unintentional in some cases. For example, the input picture is a face, eyes and hair are in different positions. And to learn different features in different positions, please (refer to [Stanford University Open Class](http://cs231n.Github.io/convolutional-networks/)). Note that the weights are only shared for the neurons of the same depth slice. In the convolutional layer, multiple sets of convolutional kernels are usually used to extract different features, that is, the weights of neurons with different depth slices are not shared by the features with different depth slices. In addition, bias are shared by all neurons with the same depth.
+- Weight sharing: The filters used to calculate neurons in the same deep slice are shared. For example, in Figure 5, the filter for each neuron calculated by $o[:,:,0]$ is the same, both are $W_0$, which can greatly reduce the parameters. The sharing weight is meaningful to a certain extent, for example, the bottom edge feature of the image is independent of the specific location of the feature in the graph. However, it is unintentional in some cases. For example, the input picture is a face, eyes and hair are in different positions. And to learn different features in different positions, please (refer to [Stanford University Open Class](http://cs231n.Github.io/convolutional-networks/)). Note that the weights are only shared for the neurons of the same depth slice. In the convolutional layer, multiple sets of convolutional kernels are usually used to extract different features, that is, the weights of neurons with different depth slices are not shared by the features with different depth slices. In addition, bias are shared by all neurons with the same depth.
 
 By introducing the calculation process of convolution and its features, convolution could be seen as a linear operation with shift-invariant, which is the same operation performed at each position of the image. The local connection and weight sharing of the convolutional layer greatly reduce the parameters that need to be learned, which helps with training larger convolutional neural networks.
 

03.image_classification/README.cn.md

@@ -597,7 +597,7 @@ with fluid.scope_guard(inference_scope):
 
 [17] Szegedy, C., Ioffe, S., Vanhoucke, V. [Inception-v4, inception-resnet and the impact of residual connections on learning](https://arxiv.org/abs/1602.07261). arXiv:1602.07261 (2016).
 
-[18] Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J. and Zisserman, A. [The Pascal Visual Object Classes Challenge: A Retrospective]((http://link.springer.com/article/10.1007/s11263-014-0733-5)). International Journal of Computer Vision, 111(1), 98-136, 2015.
+[18] Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J. and Zisserman, A. [The Pascal Visual Object Classes Challenge: A Retrospective](http://link.springer.com/article/10.1007/s11263-014-0733-5). International Journal of Computer Vision, 111(1), 98-136, 2015.
 
 [19] He, K., Zhang, X., Ren, S., and Sun, J. [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://arxiv.org/abs/1502.01852). ArXiv e-prints, February 2015.
 

03.image_classification/README.md

@@ -603,7 +603,7 @@ The traditional image classification method consists of multiple stages. The fra
 
 [17] Szegedy, C., Ioffe, S., Vanhoucke, V. [Inception-v4, inception-resnet and the impact of residual connections on learning](https://arxiv.org/abs/1602.07261). arXiv:1602.07261 (2016).
 
-[18] Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J. and Zisserman, A. [The Pascal Visual Object Classes Challenge: A Retrospective]((http://link.springer.com/article/10.1007/s11263-014-0733-5)). International Journal of Computer Vision, 111(1), 98-136, 2015.
+[18] Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J. and Zisserman, A. [The Pascal Visual Object Classes Challenge: A Retrospective](http://link.springer.com/article/10.1007/s11263-014-0733-5). International Journal of Computer Vision, 111(1), 98-136, 2015.
 
 [19] He, K., Zhang, X., Ren, S., and Sun, J. [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://arxiv.org/abs/1502.01852). ArXiv e-prints, February 2015.
 

03.image_classification/index.cn.html

@@ -639,7 +639,7 @@ with fluid.scope_guard(inference_scope):
 
 [17] Szegedy, C., Ioffe, S., Vanhoucke, V. [Inception-v4, inception-resnet and the impact of residual connections on learning](https://arxiv.org/abs/1602.07261). arXiv:1602.07261 (2016).
 
-[18] Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J. and Zisserman, A. [The Pascal Visual Object Classes Challenge: A Retrospective]((http://link.springer.com/article/10.1007/s11263-014-0733-5)). International Journal of Computer Vision, 111(1), 98-136, 2015.
+[18] Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J. and Zisserman, A. [The Pascal Visual Object Classes Challenge: A Retrospective](http://link.springer.com/article/10.1007/s11263-014-0733-5). International Journal of Computer Vision, 111(1), 98-136, 2015.
 
 [19] He, K., Zhang, X., Ren, S., and Sun, J. [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://arxiv.org/abs/1502.01852). ArXiv e-prints, February 2015.
 

03.image_classification/index.html

@@ -645,7 +645,7 @@ The traditional image classification method consists of multiple stages. The fra
 
 [17] Szegedy, C., Ioffe, S., Vanhoucke, V. [Inception-v4, inception-resnet and the impact of residual connections on learning](https://arxiv.org/abs/1602.07261). arXiv:1602.07261 (2016).
 
-[18] Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J. and Zisserman, A. [The Pascal Visual Object Classes Challenge: A Retrospective]((http://link.springer.com/article/10.1007/s11263-014-0733-5)). International Journal of Computer Vision, 111(1), 98-136, 2015.
+[18] Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J. and Zisserman, A. [The Pascal Visual Object Classes Challenge: A Retrospective](http://link.springer.com/article/10.1007/s11263-014-0733-5). International Journal of Computer Vision, 111(1), 98-136, 2015.
 
 [19] He, K., Zhang, X., Ren, S., and Sun, J. [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://arxiv.org/abs/1502.01852). ArXiv e-prints, February 2015.
 

05.recommender_system/README.cn.md

@@ -592,7 +592,7 @@ with fluid.scope_guard(inference_scope):
 2. Sarwar, Badrul, et al. "[Item-based collaborative filtering recommendation algorithms.](http://files.grouplens.org/papers/www10_sarwar.pdf)" *Proceedings of the 10th international conference on World Wide Web*. ACM, 2001.
 3. Kautz, Henry, Bart Selman, and Mehul Shah. "[Referral Web: combining social networks and collaborative filtering.](http://www.cs.cornell.edu/selman/papers/pdf/97.cacm.refweb.pdf)" Communications of the ACM 40.3 (1997): 63-65. APA
 4. [Peter Brusilovsky](https://en.wikipedia.org/wiki/Peter_Brusilovsky) (2007). *The Adaptive Web*. p. 325.
-5. Robin Burke , [Hybrid Web Recommender Systems](http://www.dcs.warwick.ac.uk/~acristea/courses/CS411/2010/Book%20-%20The%20Adaptive%20Web/HybridWebRecommenderSystems.pdf), pp. 377-408, The Adaptive Web, Peter Brusilovsky, Alfred Kobsa, Wolfgang Nejdl (Ed.), Lecture Notes in Computer Science, Springer-Verlag, Berlin, Germany, Lecture Notes in Computer Science, Vol. 4321, May 2007, 978-3-540-72078-2.
+5. Robin Burke , [Hybrid Web Recommender Systems](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.435.7538&rep=rep1&type=pdf), pp. 377-408, The Adaptive Web, Peter Brusilovsky, Alfred Kobsa, Wolfgang Nejdl (Ed.), Lecture Notes in Computer Science, Springer-Verlag, Berlin, Germany, Lecture Notes in Computer Science, Vol. 4321, May 2007, 978-3-540-72078-2.
 6. Yuan, Jianbo, et al. ["Solving Cold-Start Problem in Large-scale Recommendation Engines: A Deep Learning Approach."](https://arxiv.org/pdf/1611.05480v1.pdf) *arXiv preprint arXiv:1611.05480* (2016).
 7. Covington P, Adams J, Sargin E. [Deep neural networks for youtube recommendations](https://static.googleusercontent.com/media/research.google.com/zh-CN//pubs/archive/45530.pdf)[C]//Proceedings of the 10th ACM Conference on Recommender Systems. ACM, 2016: 191-198.
 

05.recommender_system/README.md

@@ -581,7 +581,7 @@ This chapter introduced the traditional personalized recommendation system metho
 2. Sarwar, Badrul, et al. "[Item-based collaborative filtering recommendation algorithms.](http://files.grouplens.org/papers/www10_sarwar.pdf)" *Proceedings of the 10th international conference on World Wide Web*. ACM, 2001.
 3. Kautz, Henry, Bart Selman, and Mehul Shah. "[Referral Web: combining social networks and collaborative filtering.](http://www.cs.cornell.edu/selman/papers/pdf/97.cacm.refweb.pdf)" Communications of the ACM 40.3 (1997): 63-65. APA
 4. [Peter Brusilovsky](https://en.wikipedia.org/wiki/Peter_Brusilovsky) (2007). *The Adaptive Web*. p. 325.
-5. Robin Burke , [Hybrid Web recommendation systems](http://www.dcs.warwick.ac.uk/~acristea/courses/CS411/2010/Book%20-%20The%20Adaptive%20Web/HybridWebRecommenderSystems.pdf), pp. 377-408, The Adaptive Web, Peter Brusilovsky, Alfred Kobsa, Wolfgang Nejdl (Ed.), Lecture Notes in Computer Science, Springer-Verlag, Berlin, Germany, Lecture Notes in Computer Science, Vol. 4321, May 2007, 978-3-540-72078-2.
+5. Robin Burke , [Hybrid Web recommendation systems](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.435.7538&rep=rep1&type=pdf), pp. 377-408, The Adaptive Web, Peter Brusilovsky, Alfred Kobsa, Wolfgang Nejdl (Ed.), Lecture Notes in Computer Science, Springer-Verlag, Berlin, Germany, Lecture Notes in Computer Science, Vol. 4321, May 2007, 978-3-540-72078-2.
 6. Yuan, Jianbo, et al. ["Solving Cold-Start Problem in Large-scale Recommendation Engines: A Deep Learning Approach."](https://arxiv.org/pdf/1611.05480v1.pdf) *arXiv preprint arXiv:1611.05480* (2016).
 7. Covington P, Adams J, Sargin E. [Deep neural networks for youtube recommendations](https://static.googleusercontent.com/media/research.google.com/zh-CN//pubs/archive/45530.pdf)[C]//Proceedings of the 10th ACM Conference on recommendation systems. ACM, 2016: 191-198.
 

05.recommender_system/index.cn.html

@@ -634,7 +634,7 @@ with fluid.scope_guard(inference_scope):
 2. Sarwar, Badrul, et al. "[Item-based collaborative filtering recommendation algorithms.](http://files.grouplens.org/papers/www10_sarwar.pdf)" *Proceedings of the 10th international conference on World Wide Web*. ACM, 2001.
 3. Kautz, Henry, Bart Selman, and Mehul Shah. "[Referral Web: combining social networks and collaborative filtering.](http://www.cs.cornell.edu/selman/papers/pdf/97.cacm.refweb.pdf)" Communications of the ACM 40.3 (1997): 63-65. APA
 4. [Peter Brusilovsky](https://en.wikipedia.org/wiki/Peter_Brusilovsky) (2007). *The Adaptive Web*. p. 325.
-5. Robin Burke , [Hybrid Web Recommender Systems](http://www.dcs.warwick.ac.uk/~acristea/courses/CS411/2010/Book%20-%20The%20Adaptive%20Web/HybridWebRecommenderSystems.pdf), pp. 377-408, The Adaptive Web, Peter Brusilovsky, Alfred Kobsa, Wolfgang Nejdl (Ed.), Lecture Notes in Computer Science, Springer-Verlag, Berlin, Germany, Lecture Notes in Computer Science, Vol. 4321, May 2007, 978-3-540-72078-2.
+5. Robin Burke , [Hybrid Web Recommender Systems](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.435.7538&rep=rep1&type=pdf), pp. 377-408, The Adaptive Web, Peter Brusilovsky, Alfred Kobsa, Wolfgang Nejdl (Ed.), Lecture Notes in Computer Science, Springer-Verlag, Berlin, Germany, Lecture Notes in Computer Science, Vol. 4321, May 2007, 978-3-540-72078-2.
 6. Yuan, Jianbo, et al. ["Solving Cold-Start Problem in Large-scale Recommendation Engines: A Deep Learning Approach."](https://arxiv.org/pdf/1611.05480v1.pdf) *arXiv preprint arXiv:1611.05480* (2016).
 7. Covington P, Adams J, Sargin E. [Deep neural networks for youtube recommendations](https://static.googleusercontent.com/media/research.google.com/zh-CN//pubs/archive/45530.pdf)[C]//Proceedings of the 10th ACM Conference on Recommender Systems. ACM, 2016: 191-198.
 

05.recommender_system/index.html

@@ -623,7 +623,7 @@ This chapter introduced the traditional personalized recommendation system metho
 2. Sarwar, Badrul, et al. "[Item-based collaborative filtering recommendation algorithms.](http://files.grouplens.org/papers/www10_sarwar.pdf)" *Proceedings of the 10th international conference on World Wide Web*. ACM, 2001.
 3. Kautz, Henry, Bart Selman, and Mehul Shah. "[Referral Web: combining social networks and collaborative filtering.](http://www.cs.cornell.edu/selman/papers/pdf/97.cacm.refweb.pdf)" Communications of the ACM 40.3 (1997): 63-65. APA
 4. [Peter Brusilovsky](https://en.wikipedia.org/wiki/Peter_Brusilovsky) (2007). *The Adaptive Web*. p. 325.
-5. Robin Burke , [Hybrid Web recommendation systems](http://www.dcs.warwick.ac.uk/~acristea/courses/CS411/2010/Book%20-%20The%20Adaptive%20Web/HybridWebRecommenderSystems.pdf), pp. 377-408, The Adaptive Web, Peter Brusilovsky, Alfred Kobsa, Wolfgang Nejdl (Ed.), Lecture Notes in Computer Science, Springer-Verlag, Berlin, Germany, Lecture Notes in Computer Science, Vol. 4321, May 2007, 978-3-540-72078-2.
+5. Robin Burke , [Hybrid Web recommendation systems](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.435.7538&rep=rep1&type=pdf), pp. 377-408, The Adaptive Web, Peter Brusilovsky, Alfred Kobsa, Wolfgang Nejdl (Ed.), Lecture Notes in Computer Science, Springer-Verlag, Berlin, Germany, Lecture Notes in Computer Science, Vol. 4321, May 2007, 978-3-540-72078-2.
 6. Yuan, Jianbo, et al. ["Solving Cold-Start Problem in Large-scale Recommendation Engines: A Deep Learning Approach."](https://arxiv.org/pdf/1611.05480v1.pdf) *arXiv preprint arXiv:1611.05480* (2016).
 7. Covington P, Adams J, Sargin E. [Deep neural networks for youtube recommendations](https://static.googleusercontent.com/media/research.google.com/zh-CN//pubs/archive/45530.pdf)[C]//Proceedings of the 10th ACM Conference on recommendation systems. ACM, 2016: 191-198.
 

06.understand_sentiment/README.cn.md

@@ -170,7 +170,7 @@ def convolution_net(data, input_dim, class_dim, emb_dim, hid_dim):
     return prediction
 ```
 
-网络的输入`input_dim`表示的是词典的大小，`class_dim`表示类别数。这里，我们使用[`sequence_conv_pool`](https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/trainer_config_helpers/networks.py) API实现了卷积和池化操作。
+网络的输入`input_dim`表示的是词典的大小，`class_dim`表示类别数。这里，我们使用[`sequence_conv_pool`](https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/fluid/nets.py) API实现了卷积和池化操作。
 
 <a name="栈值双向LSTM"></a>
 

06.understand_sentiment/README.md

@@ -159,7 +159,7 @@ def convolution_net(data, input_dim, class_dim, emb_dim, hid_dim):
     return prediction
 ```
 
-The network input `input_dim` indicates the size of the dictionary, and `class_dim` indicates the number of categories. Here, we implement the convolution and pooling operations using the [`sequence_conv_pool`](https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/trainer_config_helpers/networks.py) API.
+The network input `input_dim` indicates the size of the dictionary, and `class_dim` indicates the number of categories. Here, we implement the convolution and pooling operations using the [`sequence_conv_pool`](https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/fluid/nets.py) API.
 
 <a name="Stack value bidirectional LSTM"></a>
 

06.understand_sentiment/index.cn.html

@@ -212,7 +212,7 @@ def convolution_net(data, input_dim, class_dim, emb_dim, hid_dim):
     return prediction
 ```
 
-网络的输入`input_dim`表示的是词典的大小，`class_dim`表示类别数。这里，我们使用[`sequence_conv_pool`](https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/trainer_config_helpers/networks.py) API实现了卷积和池化操作。
+网络的输入`input_dim`表示的是词典的大小，`class_dim`表示类别数。这里，我们使用[`sequence_conv_pool`](https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/fluid/nets.py) API实现了卷积和池化操作。
 
 <a name="栈值双向LSTM"></a>
 

06.understand_sentiment/index.html

@@ -201,7 +201,7 @@ def convolution_net(data, input_dim, class_dim, emb_dim, hid_dim):
     return prediction
 ```
 
-The network input `input_dim` indicates the size of the dictionary, and `class_dim` indicates the number of categories. Here, we implement the convolution and pooling operations using the [`sequence_conv_pool`](https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/trainer_config_helpers/networks.py) API.
+The network input `input_dim` indicates the size of the dictionary, and `class_dim` indicates the number of categories. Here, we implement the convolution and pooling operations using the [`sequence_conv_pool`](https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/fluid/nets.py) API.
 
 <a name="Stack value bidirectional LSTM"></a>
 

07.label_semantic_roles/README.cn.md

@@ -561,7 +561,7 @@ print("Inference Shape: ", np_data.shape)
 2. Pascanu R, Gulcehre C, Cho K, et al. [How to construct deep recurrent neural networks](https://arxiv.org/abs/1312.6026)[J]. arXiv preprint arXiv:1312.6026, 2013.
 3. Cho K, Van Merriënboer B, Gulcehre C, et al. [Learning phrase representations using RNN encoder-decoder for statistical machine translation](https://arxiv.org/abs/1406.1078)[J]. arXiv preprint arXiv:1406.1078, 2014.
 4. Bahdanau D, Cho K, Bengio Y. [Neural machine translation by jointly learning to align and translate](https://arxiv.org/abs/1409.0473)[J]. arXiv preprint arXiv:1409.0473, 2014.
-5. Lafferty J, McCallum A, Pereira F. [Conditional random fields: Probabilistic models for segmenting and labeling sequence data](http://www.jmlr.org/papers/volume15/doppa14a/source/biblio.bib.old)[C]//Proceedings of the eighteenth international conference on machine learning, ICML. 2001, 1: 282-289.
+5. Lafferty J, McCallum A, Pereira F. [Conditional random fields: Probabilistic models for segmenting and labeling sequence data](https://repository.upenn.edu/cgi/viewcontent.cgi?article=1162&context=cis_papers)[C]//Proceedings of the eighteenth international conference on machine learning, ICML. 2001, 1: 282-289.
 6. 李航. 统计学习方法[J]. 清华大学出版社, 北京, 2012.
 7. Marcus M P, Marcinkiewicz M A, Santorini B. [Building a large annotated corpus of English: The Penn Treebank](http://repository.upenn.edu/cgi/viewcontent.cgi?article=1246&context=cis_reports)[J]. Computational linguistics, 1993, 19(2): 313-330.
 8. Palmer M, Gildea D, Kingsbury P. [The proposition bank: An annotated corpus of semantic roles](http://www.mitpressjournals.org/doi/pdfplus/10.1162/0891201053630264)[J]. Computational linguistics, 2005, 31(1): 71-106.

07.label_semantic_roles/README.md

@@ -545,7 +545,7 @@ Labeling semantic roles is an important intermediate step in many natural langua
 2. Pascanu R, Gulcehre C, Cho K, et al. [How to construct deep recurrent neural networks](https://arxiv.org/abs/1312.6026)[J]. arXiv preprint arXiv:1312.6026, 2013.
 3. Cho K, Van Merriënboer B, Gulcehre C, et al. [Learning phrase representations using RNN encoder-decoder for statistical machine translation](https://arxiv.org/abs/1406.1078)[J]. arXiv preprint arXiv: 1406.1078, 2014.
 4. Bahdanau D, Cho K, Bengio Y. [Neural machine translation by jointly learning to align and translate](https://arxiv.org/abs/1409.0473)[J]. arXiv preprint arXiv:1409.0473, 2014.
-5. Lafferty J, McCallum A, Pereira F. [Conditional random fields: Probabilistic models for segmenting and labeling sequence data](http://www.jmlr.org/papers/volume15/doppa14a/source/biblio.bib.old) [C]//Proceedings of the eighteenth international conference on machine learning, ICML. 2001, 1: 282-289.
+5. Lafferty J, McCallum A, Pereira F. [Conditional random fields: Probabilistic models for segmenting and labeling sequence data](https://repository.upenn.edu/cgi/viewcontent.cgi?article=1162&context=cis_papers) [C]//Proceedings of the eighteenth international conference on machine learning, ICML. 2001, 1: 282-289.
 6. Li Hang. Statistical Learning Method[J]. Tsinghua University Press, Beijing, 2012.
 7. Marcus MP, Marcinkiewicz MA, Santorini B. [Building a large annotated corpus of English: The Penn Treebank](http://repository.upenn.edu/cgi/viewcontent.cgi?article=1246&context=cis_reports)[J] Computational linguistics, 1993, 19(2): 313-330.
 8. Palmer M, Gildea D, Kingsbury P. [The proposition bank: An annotated corpus of semantic roles](http://www.mitpressjournals.org/doi/pdfplus/10.1162/0891201053630264) [J]. Computational linguistics, 2005 , 31(1): 71-106.

07.label_semantic_roles/index.cn.html

@@ -603,7 +603,7 @@ print("Inference Shape: ", np_data.shape)
 2. Pascanu R, Gulcehre C, Cho K, et al. [How to construct deep recurrent neural networks](https://arxiv.org/abs/1312.6026)[J]. arXiv preprint arXiv:1312.6026, 2013.
 3. Cho K, Van Merriënboer B, Gulcehre C, et al. [Learning phrase representations using RNN encoder-decoder for statistical machine translation](https://arxiv.org/abs/1406.1078)[J]. arXiv preprint arXiv:1406.1078, 2014.
 4. Bahdanau D, Cho K, Bengio Y. [Neural machine translation by jointly learning to align and translate](https://arxiv.org/abs/1409.0473)[J]. arXiv preprint arXiv:1409.0473, 2014.
-5. Lafferty J, McCallum A, Pereira F. [Conditional random fields: Probabilistic models for segmenting and labeling sequence data](http://www.jmlr.org/papers/volume15/doppa14a/source/biblio.bib.old)[C]//Proceedings of the eighteenth international conference on machine learning, ICML. 2001, 1: 282-289.
+5. Lafferty J, McCallum A, Pereira F. [Conditional random fields: Probabilistic models for segmenting and labeling sequence data](https://repository.upenn.edu/cgi/viewcontent.cgi?article=1162&context=cis_papers)[C]//Proceedings of the eighteenth international conference on machine learning, ICML. 2001, 1: 282-289.
 6. 李航. 统计学习方法[J]. 清华大学出版社, 北京, 2012.
 7. Marcus M P, Marcinkiewicz M A, Santorini B. [Building a large annotated corpus of English: The Penn Treebank](http://repository.upenn.edu/cgi/viewcontent.cgi?article=1246&context=cis_reports)[J]. Computational linguistics, 1993, 19(2): 313-330.
 8. Palmer M, Gildea D, Kingsbury P. [The proposition bank: An annotated corpus of semantic roles](http://www.mitpressjournals.org/doi/pdfplus/10.1162/0891201053630264)[J]. Computational linguistics, 2005, 31(1): 71-106.

07.label_semantic_roles/index.html

@@ -587,7 +587,7 @@ Labeling semantic roles is an important intermediate step in many natural langua
 2. Pascanu R, Gulcehre C, Cho K, et al. [How to construct deep recurrent neural networks](https://arxiv.org/abs/1312.6026)[J]. arXiv preprint arXiv:1312.6026, 2013.
 3. Cho K, Van Merriënboer B, Gulcehre C, et al. [Learning phrase representations using RNN encoder-decoder for statistical machine translation](https://arxiv.org/abs/1406.1078)[J]. arXiv preprint arXiv: 1406.1078, 2014.
 4. Bahdanau D, Cho K, Bengio Y. [Neural machine translation by jointly learning to align and translate](https://arxiv.org/abs/1409.0473)[J]. arXiv preprint arXiv:1409.0473, 2014.
-5. Lafferty J, McCallum A, Pereira F. [Conditional random fields: Probabilistic models for segmenting and labeling sequence data](http://www.jmlr.org/papers/volume15/doppa14a/source/biblio.bib.old) [C]//Proceedings of the eighteenth international conference on machine learning, ICML. 2001, 1: 282-289.
+5. Lafferty J, McCallum A, Pereira F. [Conditional random fields: Probabilistic models for segmenting and labeling sequence data](https://repository.upenn.edu/cgi/viewcontent.cgi?article=1162&context=cis_papers) [C]//Proceedings of the eighteenth international conference on machine learning, ICML. 2001, 1: 282-289.
 6. Li Hang. Statistical Learning Method[J]. Tsinghua University Press, Beijing, 2012.
 7. Marcus MP, Marcinkiewicz MA, Santorini B. [Building a large annotated corpus of English: The Penn Treebank](http://repository.upenn.edu/cgi/viewcontent.cgi?article=1246&context=cis_reports)[J] Computational linguistics, 1993, 19(2): 313-330.
 8. Palmer M, Gildea D, Kingsbury P. [The proposition bank: An annotated corpus of semantic roles](http://www.mitpressjournals.org/doi/pdfplus/10.1162/0891201053630264) [J]. Computational linguistics, 2005 , 31(1): 71-106.