Basic Linear Classification for Image


Linear classifier. In this module we will start out with arguably the simplest possible function, a linear mapping:
Where we are assuming that the image xi has all of its pixels flattened out to a single column vector of shape [D x 1]. The matrix W (of size [K x D]), and the vector b (of size [K x 1]) are the parameters of the function. In CIFAR-10, xi contains all pixels in the i-th image flattened into a single [3072 x 1] column, W is [10 x 3072] and b is [10 x 1], so 3072 numbers come into the function (the raw pixel values) and 10 numbers come out (the class scores).

Convolutional Neural Networks will map image pixels to scores exactly as shown above, but the mapping ( f ) will be more complex and will contain more parameters.
A simplify example of mentioned linear classification



Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s