Creating Separable Encodings of Images
Learn about how images can be compressed into numerical vectors using neural networks.
We'll cover the following
Let’s examine how neural networks can optimally compress information into numerical vectors. To do so, each element of the vector should encode distinct information from the others, a property we can achieve using a variational objective. This variational objective is the building block for creating VAE networks.
In the figure below, you can see an example of images from the CIFAR-10
Get hands-on with 1400+ tech skills courses.