In this article, we are going to talk about adversarial attacks and discuss their implications for deep learning model and their security.
Latent space visualization
Today, we will see how autoencoders can help us visualize the data in some very cool ways. For that, we will work on images, using the Convolutional Autoencoder architecture (CAE).
Autoencoders
Autoencoders (AE) are a family of neural networks for which the input is the same as the output*. They work by compressing the input into a latent-spacerepresentation, and then reconstructing the output from this representation.