Cargando…

Iterative Deep Neighborhood: A Deep Learning Model Which Involves Both Input Data Points and Their Neighbors

Deep learning models, such as deep convolutional neural network and deep long-short term memory model, have achieved great successes in many pattern classification applications over shadow machine learning models with hand-crafted features. The main reason is the ability of deep learning models to a...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu, Rong, Liu, Yan, Yan, Yonggang, Wang, Jing-Yan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7199621/
https://www.ncbi.nlm.nih.gov/pubmed/32405299
http://dx.doi.org/10.1155/2020/9868017
_version_ 1783529183076417536
author Liu, Rong
Liu, Yan
Yan, Yonggang
Wang, Jing-Yan
author_facet Liu, Rong
Liu, Yan
Yan, Yonggang
Wang, Jing-Yan
author_sort Liu, Rong
collection PubMed
description Deep learning models, such as deep convolutional neural network and deep long-short term memory model, have achieved great successes in many pattern classification applications over shadow machine learning models with hand-crafted features. The main reason is the ability of deep learning models to automatically extract hierarchical features from massive data by multiple layers of neurons. However, in many other situations, existing deep learning models still cannot gain satisfying results due to the limitation of the inputs of models. The existing deep learning models only take the data instances of an input point but completely ignore the other data points in the dataset, which potentially provides critical insight for the classification of the given input. To overcome this gap, in this paper, we show that the neighboring data points besides the input data point itself can boost the deep learning model's performance significantly and design a novel deep learning model which takes both the data instances of an input point and its neighbors' classification responses as inputs. In addition, we develop an iterative algorithm which updates the neighbors of data points according to the deep representations output by the deep learning model and the parameters of the deep learning model alternately. The proposed algorithm, named “Iterative Deep Neighborhood (IDN),” shows its advantages over the state-of-the-art deep learning models over tasks of image classification, text sentiment analysis, property price trend prediction, etc.
format Online
Article
Text
id pubmed-7199621
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Hindawi
record_format MEDLINE/PubMed
spelling pubmed-71996212020-05-13 Iterative Deep Neighborhood: A Deep Learning Model Which Involves Both Input Data Points and Their Neighbors Liu, Rong Liu, Yan Yan, Yonggang Wang, Jing-Yan Comput Intell Neurosci Research Article Deep learning models, such as deep convolutional neural network and deep long-short term memory model, have achieved great successes in many pattern classification applications over shadow machine learning models with hand-crafted features. The main reason is the ability of deep learning models to automatically extract hierarchical features from massive data by multiple layers of neurons. However, in many other situations, existing deep learning models still cannot gain satisfying results due to the limitation of the inputs of models. The existing deep learning models only take the data instances of an input point but completely ignore the other data points in the dataset, which potentially provides critical insight for the classification of the given input. To overcome this gap, in this paper, we show that the neighboring data points besides the input data point itself can boost the deep learning model's performance significantly and design a novel deep learning model which takes both the data instances of an input point and its neighbors' classification responses as inputs. In addition, we develop an iterative algorithm which updates the neighbors of data points according to the deep representations output by the deep learning model and the parameters of the deep learning model alternately. The proposed algorithm, named “Iterative Deep Neighborhood (IDN),” shows its advantages over the state-of-the-art deep learning models over tasks of image classification, text sentiment analysis, property price trend prediction, etc. Hindawi 2020-01-02 /pmc/articles/PMC7199621/ /pubmed/32405299 http://dx.doi.org/10.1155/2020/9868017 Text en Copyright © 2020 Rong Liu et al. http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Liu, Rong
Liu, Yan
Yan, Yonggang
Wang, Jing-Yan
Iterative Deep Neighborhood: A Deep Learning Model Which Involves Both Input Data Points and Their Neighbors
title Iterative Deep Neighborhood: A Deep Learning Model Which Involves Both Input Data Points and Their Neighbors
title_full Iterative Deep Neighborhood: A Deep Learning Model Which Involves Both Input Data Points and Their Neighbors
title_fullStr Iterative Deep Neighborhood: A Deep Learning Model Which Involves Both Input Data Points and Their Neighbors
title_full_unstemmed Iterative Deep Neighborhood: A Deep Learning Model Which Involves Both Input Data Points and Their Neighbors
title_short Iterative Deep Neighborhood: A Deep Learning Model Which Involves Both Input Data Points and Their Neighbors
title_sort iterative deep neighborhood: a deep learning model which involves both input data points and their neighbors
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7199621/
https://www.ncbi.nlm.nih.gov/pubmed/32405299
http://dx.doi.org/10.1155/2020/9868017
work_keys_str_mv AT liurong iterativedeepneighborhoodadeeplearningmodelwhichinvolvesbothinputdatapointsandtheirneighbors
AT liuyan iterativedeepneighborhoodadeeplearningmodelwhichinvolvesbothinputdatapointsandtheirneighbors
AT yanyonggang iterativedeepneighborhoodadeeplearningmodelwhichinvolvesbothinputdatapointsandtheirneighbors
AT wangjingyan iterativedeepneighborhoodadeeplearningmodelwhichinvolvesbothinputdatapointsandtheirneighbors