Application of generative deep learning models for approximation of image distribution density
A. V. Yashchenko, Alexey S. Potapov, Sergey A. Rodionov, Innokentii Zhdanov, Oleksandr V. Shcherbakov, Maxim Peterson · Journal of Optical Technology · 2019
Generative neural network models for visual concept learning and the problem of approximating image distribution density are studied. A criterion for an image to belong to a simulated class is introduced based on an estimate of the probability in the space of latent variables and reconstruction errors. Several generative deep learning models are compared. Quality estimates of the solution to the problem of one-class classifications for a set of images of handwritten digits are experimentally obtained.