3: Visualization of the latent spaces generated by three different variational autoencoder (VAE) instances trained on the same MNIST data.

3: Visualization of the latent spaces generated by three different variational autoencoder (VAE) instances trained on the same MNIST data.

Source publication
Preprint
Full-text available
Interactive exploration of large, multidimensional datasets plays a very important role in various scientific fields. It makes it possible not only to identify important structural features and forms, such as clusters of vertices and their connection patterns, but also to evaluate their interrelationships in terms of position, distance, shape and c...

Similar publications

Preprint
Full-text available
We propose a framework for achieving perfect synchronization in complex networks of Sakaguchi-Kuramoto oscillators in presence of higher order interactions (simplicial complexes) at a targeted point in the parameter space. It is achieved by using an analytically derived frequency set from the governing equations. The frequency set not only provides...