[GitHub] pracheer commented on a change in pull request #9125: Fixed incorrect wording in mnist tutorial

[GitBox <gi...@apache.org>]

pracheer commented on a change in pull request #9125: Fixed incorrect wording in mnist tutorial
URL: https://github.com/apache/incubator-mxnet/pull/9125#discussion_r157583523
 
 

 ##########
 File path: docs/tutorials/python/mnist.md
 ##########
 @@ -57,7 +57,7 @@ data = mx.sym.flatten(data=data)
 ```
 One might wonder if we are discarding valuable information by flattening. That is indeed true and we'll cover this more when we talk about convolutional neural networks where we preserve the input shape. For now, we'll go ahead and work with flattened images.
 
-MLPs contains several fully connected layers. A fully connected layer or FC layer for short, is one where each neuron in the layer is connected to every neuron in its preceding layer. From a linear algebra perspective, an FC layer applies an [affine transform](https://en.wikipedia.org/wiki/Affine_transformation) to the *n x m* input matrix *X* and outputs a matrix *Y* of size *n x k*, where *k* is the number of neurons in the FC layer. *k* is also referred to as the hidden size. The output *Y* is computed according to the equation *Y = W X + b*. The FC layer has two learnable parameters, the *m x k* weight matrix *W* and the *m x 1* bias vector *b*.
+MLPs contains several fully connected layers. A fully connected layer or FC layer for short, is one where each neuron in the layer is connected to every neuron in its preceding layer. From a linear algebra perspective, an FC layer applies an [affine transform](https://en.wikipedia.org/wiki/Affine_transformation) to the *n x m* input matrix *X* and outputs a matrix *Y* of size *n x k*, where *k* is the number of neurons in the FC layer. *k* is also referred to as the hidden size. The output *Y* is computed according to the equation *Y = X W<sup>T</sup> + b*. The FC layer has two learnable parameters, the *k x m* weight matrix *W* and the *1 x k* bias vector *b*.
 
 Review comment:
   "hidden size" is sounding a bit off. Is it only me? If not, probably "hidden layer size" or something like it may be better?
   
   Another nitpick: bias vector dimension doesn't match in the number of rows with the output of X W<sup>T</sup>. Should we hint at broadcasting?
   
   looks good to me otherwise.

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services