CODEWITHSUNDEEP
computer-visionconv-neural-networkconvolution
user8314628
user8314628

Reputation: 2042

How CNN reduce parameter and reuse weight?

In the post A Comprehensive Guide to Convolutional Neural Networks — the ELI5 way, it says

A ConvNet is able to successfully capture the Spatial and Temporal dependencies in an image through the application of relevant filters. The architecture performs a better fitting to the image dataset due to the reduction in the number of parameters involved and reusability of weights.

I don't see how it reduce parameter and reuse weight. Could anyone give an example?

Upvotes: 1

Views: 2251

Answers (2)

Prasant kumar
Prasant kumar

Reputation: 65

We can calculate the parameters for the Convolution layer using the formula: ((width_of_Kernel * height_of_Kernel * input_channel)+1) * output_channel

Here we can see Kernel size, Input Channel and, Output Channel are affecting number of parameters. By altering them, we can reduce the parameters and it will result in reducing size.

Upvotes: 0

Abhi25t
Abhi25t

Reputation: 4643

Consider the filter (or kernel) in image below having 9 pixels and the image having 49 pixels.

In a fully connected layer, we'll have 9*49 = 441 weights.

While in a CNN this same filter keeps on moving (convolving) over the entire image. All pixel values in image will be multiplied with those same 9 values of filter (hence we say weights are reused). So, we need just 9 weights per filter instead of 441 in FC layer.

The job of a filter is to identify features (such as texture, lines etc), which could be anywhere in an image. So, we want to reuse this same filter over the entire image.

enter image description here

Upvotes: 1

Related Questions