Bidirectional Variational Autoencoders

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kosko, Bart, Adigun, Olaoluwa
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916760152702976
author Kosko, Bart
Adigun, Olaoluwa
author_facet Kosko, Bart
Adigun, Olaoluwa
contents We present the new bidirectional variational autoencoder (BVAE) network architecture. The BVAE uses a single neural network both to encode and decode instead of an encoder-decoder network pair. The network encodes in the forward direction and decodes in the backward direction through the same synaptic web. Simulations compared BVAEs and ordinary VAEs on the four image tasks of image reconstruction, classification, interpolation, and generation. The image datasets included MNIST handwritten digits, Fashion-MNIST, CIFAR-10, and CelebA-64 face images. The bidirectional structure of BVAEs cut the parameter count by almost 50% and still slightly outperformed the unidirectional VAEs.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16074
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bidirectional Variational Autoencoders
Kosko, Bart
Adigun, Olaoluwa
Machine Learning
Artificial Intelligence
We present the new bidirectional variational autoencoder (BVAE) network architecture. The BVAE uses a single neural network both to encode and decode instead of an encoder-decoder network pair. The network encodes in the forward direction and decodes in the backward direction through the same synaptic web. Simulations compared BVAEs and ordinary VAEs on the four image tasks of image reconstruction, classification, interpolation, and generation. The image datasets included MNIST handwritten digits, Fashion-MNIST, CIFAR-10, and CelebA-64 face images. The bidirectional structure of BVAEs cut the parameter count by almost 50% and still slightly outperformed the unidirectional VAEs.
title Bidirectional Variational Autoencoders
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.16074