This is achieved by reformulating the modeled fluid density as an unnormalized probability distribution from which we sample with dynamic Monte Carlo methods.
These networks represent functions that are guaranteed to have connected level sets forming smooth manifolds on the input space.
The Neural Tangent Kernel (NTK) is an important milestone in the ongoing effort to build a theory for deep learning.
The real-world applicability of the proposed method is demonstrated by exploring archetypes of female facial expressions while using multi-rater based emotion scores of these expressions as side information.
"Deep Archetypal Analysis" generates latent representations of high-dimensional datasets in terms of fractions of intuitively understandable basic entities called archetypes.