You are on page 1of 2

Assignment#08-DL-Theory

Submission Deadline is 17-June-2020


Question#01
Consider the following Convolutional Neural Networks:

These are the different variants of CNN (Simple, Le-Net and Alex-Net). Compare the above
given networks in term of Input, arrangements of layers, parameters required, computational
complexity and training and give your own opinion which one do you think is better.

Page 1 of 2
Alex Net inputs start with 227 x 227 x 3 images. Then the first layers it applies 96 11 by 11 filter
with the stride of 4. Because it’s using a stride of 4 the dimension reduces to 55 by 55. Then
apply max polling with 3 by 3 filter and stride of 2 and the volume reduces to 27 by 27 by 96.
Then it applies 5 by SAME padding convolution and up with 27 by 27 by 276. Then again, a
max-pooling with 3 by 3 filter and stride of 2 and end up with 13 x 13 x 256. Then another 3 x 3
same padding convolution and up with 13 x 13 x 384. Then 3 by 3 same convolution again and
end up with 13 x 13 x 384. Then same convolution, a max pool and end up with 6 x 6 x 256,
which is 9216 parameters. Then we going to connect it with a 4096 fully connected node. Then
another fully connected layer and use a SoftMa0078 function in 1000 classes output.
As over all alex Net is better than other network because firstly it has ability to take image in
three different of RGB, black and white and gray as in other system this possibility not have

Page 2 of 2

You might also like