# Generative Model for Autoencoders Learning by Image Sampling Representations

### V. Antsiperov

#### 2022

#### Abstract

The article substantiates a generative model for autoencoders, learning by the input image representation based on a sample of random counts. This representation is used instead of the ideal image model, which usually involves too cumbersome descriptions of the source data. So, the reduction of the ideal image concept to sampling representations of fixed (controlled) size is one of the main goals of the article. It is shown that the corresponding statistical description of the sampling representation can be factorized into the product of the distributions of individual counts, which fits well into the naive Bayesian approach and some other machine learning procedures. Guided by that association the analogue of the well-known EM algorithm – the iterative partition–maximization procedure for generative autoencoders is synthesized. So, the second main goal of the article is to substantiate the partition–maximization procedure basing on the relation between autoencoder image restoration criteria and statistical maximum likelihood parameters estimation. We succeed this by modelling the input count probability distribution by the parameterized mixtures, considering the hidden mixture variables as autoencoder’s internal (coding) data.

Download#### Paper Citation

#### in Harvard Style

Antsiperov V. (2022). **Generative Model for Autoencoders Learning by Image Sampling Representations**. In *Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,* ISBN 978-989-758-549-4, pages 354-361. DOI: 10.5220/0010915200003122

#### in Bibtex Style

@conference{icpram22,

author={V. Antsiperov},

title={Generative Model for Autoencoders Learning by Image Sampling Representations},

booktitle={Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},

year={2022},

pages={354-361},

publisher={SciTePress},

organization={INSTICC},

doi={10.5220/0010915200003122},

isbn={978-989-758-549-4},

}

#### in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,

TI - Generative Model for Autoencoders Learning by Image Sampling Representations

SN - 978-989-758-549-4

AU - Antsiperov V.

PY - 2022

SP - 354

EP - 361

DO - 10.5220/0010915200003122