Cargando…
Learning Hierarchical Representations with Spike-and-Slab Inception Network
Recently, deep convolutional neural networks (CNN) with inception modules have attracted much attention due to their excellent performances on diverse domains. Nevertheless, the basic CNN can only capture a univariate feature, which is essentially linear. It leads to a weak ability in feature expres...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8512231/ https://www.ncbi.nlm.nih.gov/pubmed/34640708 http://dx.doi.org/10.3390/s21196382 |
_version_ | 1784582941587800064 |
---|---|
author | Qiao, Weizheng Bi, Xiaojun |
author_facet | Qiao, Weizheng Bi, Xiaojun |
author_sort | Qiao, Weizheng |
collection | PubMed |
description | Recently, deep convolutional neural networks (CNN) with inception modules have attracted much attention due to their excellent performances on diverse domains. Nevertheless, the basic CNN can only capture a univariate feature, which is essentially linear. It leads to a weak ability in feature expression, further resulting in insufficient feature mining. In view of this issue, researchers incessantly deepened the network, bringing parameter redundancy and model over-fitting. Hence, whether we can employ this efficient deep neural network architecture to improve CNN and enhance the capacity of image recognition task still remains unknown. In this paper, we introduce spike-and-slab units to the modified inception module, enabling our model to capture dual latent variables and the average and covariance information. This operation further enhances the robustness of our model to variations of image intensity without increasing the model parameters. The results of several tasks demonstrated that dual variable operations can be well-integrated into inception modules, and excellent results have been achieved. |
format | Online Article Text |
id | pubmed-8512231 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-85122312021-10-14 Learning Hierarchical Representations with Spike-and-Slab Inception Network Qiao, Weizheng Bi, Xiaojun Sensors (Basel) Article Recently, deep convolutional neural networks (CNN) with inception modules have attracted much attention due to their excellent performances on diverse domains. Nevertheless, the basic CNN can only capture a univariate feature, which is essentially linear. It leads to a weak ability in feature expression, further resulting in insufficient feature mining. In view of this issue, researchers incessantly deepened the network, bringing parameter redundancy and model over-fitting. Hence, whether we can employ this efficient deep neural network architecture to improve CNN and enhance the capacity of image recognition task still remains unknown. In this paper, we introduce spike-and-slab units to the modified inception module, enabling our model to capture dual latent variables and the average and covariance information. This operation further enhances the robustness of our model to variations of image intensity without increasing the model parameters. The results of several tasks demonstrated that dual variable operations can be well-integrated into inception modules, and excellent results have been achieved. MDPI 2021-09-24 /pmc/articles/PMC8512231/ /pubmed/34640708 http://dx.doi.org/10.3390/s21196382 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Qiao, Weizheng Bi, Xiaojun Learning Hierarchical Representations with Spike-and-Slab Inception Network |
title | Learning Hierarchical Representations with Spike-and-Slab Inception Network |
title_full | Learning Hierarchical Representations with Spike-and-Slab Inception Network |
title_fullStr | Learning Hierarchical Representations with Spike-and-Slab Inception Network |
title_full_unstemmed | Learning Hierarchical Representations with Spike-and-Slab Inception Network |
title_short | Learning Hierarchical Representations with Spike-and-Slab Inception Network |
title_sort | learning hierarchical representations with spike-and-slab inception network |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8512231/ https://www.ncbi.nlm.nih.gov/pubmed/34640708 http://dx.doi.org/10.3390/s21196382 |
work_keys_str_mv | AT qiaoweizheng learninghierarchicalrepresentationswithspikeandslabinceptionnetwork AT bixiaojun learninghierarchicalrepresentationswithspikeandslabinceptionnetwork |