# π Advanced Concepts

Advanced Concepts About Convolutional Neural Networks

# Important Terms

 Term Description π· Padding Adding additional border(s) to the image before convolution π  Strided Convolution Convolving by s steps π Convolutions Over Volume Applying convs on n-dimensional input (such as an RGB image)

# π Padding

Adding an additional one border or more to the image so the image is n+2 x n+2 and after convolution we end up with n x n image which is the original size of the image

p = number of added borders

For convention: it is filled by 0

# π€ How much to pad?

For better understanding let's say that we have two concepts:

## π΅οΈββοΈ Valid Convolutions

It means no padding so:

n x n * f x f β‘ n-f+1 x n-f+1

## π₯½ Same Convolutions

Pad so that output size is the same as the input size.

So we want that π§:

n+2p-f+1 = n

Hence:

p = (f-1)/2

For convention f is chosen to be odd π©βπ

# π’ Strided Convolution

Another approach of convolutions, we calculate the output by applying filter on regions by some value s.

# π€ To Generalize

For an n x n image and f x f filter, with p padding and stride s; the output image size can be calculated by the following formula

β$\left \lfloor{\frac{n+2p-f}{s}+1}\right \rfloor \times \left \lfloor{\frac{n+2p-f}{s}+1}\right \rfloor$β

# π Convolutions Over Volume

To apply convolution operation on an RGB image; for example on 10x10 px RGB image, technically the image's dimension is 10x10x3 so we can apply for example a 3x3x3 filter or fxfx3 π€³

Filters can be applied on a special color channel π¨

# π¨ Types of Layer In A Convolutional Network

 Layer Description π« Convolution CONV Filters to extract features π Pooling POOL A technique to reduce size of representation and to speed up the computations β­ Fully Connected FC Standard single neural network layer (one dimensional)

π©βπ« Usually when people report number of layers in an NN they just report the number of layers that have weights and params

Convention: CONV1 + POOL1 = LAYER1

# π€ Why Convolotions?

• Better performance since they decrease the parameters that will be tuned π«