Pyramidal Predictive Network: A Model for Visual-frame Prediction Based on Predictive Coding Theory

Visual-frame prediction is a pixel-dense prediction task that infers future frames from past frames. Lacking of appearance details, low prediction accuracy and high computational overhead are still major problems with current models or methods. In this paper, we propose a novel neural network model...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2022-11
Hauptverfasser: Ling, Chaofan, Zhong, Junpei, Li, Weihua
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Ling, Chaofan
Zhong, Junpei
Li, Weihua
description Visual-frame prediction is a pixel-dense prediction task that infers future frames from past frames. Lacking of appearance details, low prediction accuracy and high computational overhead are still major problems with current models or methods. In this paper, we propose a novel neural network model inspired by the well-known predictive coding theory to deal with the problems. Predictive coding provides an interesting and reliable computational framework, which will be combined with other theories such as the cerebral cortex at different level oscillates at different frequencies, to design an efficient and reliable predictive network model for visual-frame prediction. Specifically, the model is composed of a series of recurrent and convolutional units forming the top-down and bottom-up streams, respectively. The update frequency of neural units on each of the layer decreases with the increasing of network levels, which results in neurons of higher-level can capture information in longer time dimensions. According to the experimental results, this model shows better compactness and comparable predictive performance with existing works, implying lower computational cost and higher prediction accuracy. Code is available at https://github.com/Ling-CF/PPNet.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2702668994</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2702668994</sourcerecordid><originalsourceid>FETCH-proquest_journals_27026689943</originalsourceid><addsrcrecordid>eNqNjj0LwjAURYMgWLT_4YFzoSb9dNOiuCgOxbWE5lVTY6NJq_Tf20HE0ekeuIfLHRGHMrbwkoDSCXGtrX3fp1FMw5A5pDz2ht-k4AqOBoUsW_lEOGD70ua6hBXstUAFlTZwkrbjyqsGH7-ybmDNLQoY4Gcg00I2Z8gvqE0_I-OKK4vuJ6dkvt3k2c67G_3o0LZFrTvTDFVB4-FalKRpwP6z3n1QRXg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2702668994</pqid></control><display><type>article</type><title>Pyramidal Predictive Network: A Model for Visual-frame Prediction Based on Predictive Coding Theory</title><source>Free E- Journals</source><creator>Ling, Chaofan ; Zhong, Junpei ; Li, Weihua</creator><creatorcontrib>Ling, Chaofan ; Zhong, Junpei ; Li, Weihua</creatorcontrib><description>Visual-frame prediction is a pixel-dense prediction task that infers future frames from past frames. Lacking of appearance details, low prediction accuracy and high computational overhead are still major problems with current models or methods. In this paper, we propose a novel neural network model inspired by the well-known predictive coding theory to deal with the problems. Predictive coding provides an interesting and reliable computational framework, which will be combined with other theories such as the cerebral cortex at different level oscillates at different frequencies, to design an efficient and reliable predictive network model for visual-frame prediction. Specifically, the model is composed of a series of recurrent and convolutional units forming the top-down and bottom-up streams, respectively. The update frequency of neural units on each of the layer decreases with the increasing of network levels, which results in neurons of higher-level can capture information in longer time dimensions. According to the experimental results, this model shows better compactness and comparable predictive performance with existing works, implying lower computational cost and higher prediction accuracy. Code is available at https://github.com/Ling-CF/PPNet.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Coding theory ; Neural networks ; Performance prediction ; Visual tasks</subject><ispartof>arXiv.org, 2022-11</ispartof><rights>2022. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Ling, Chaofan</creatorcontrib><creatorcontrib>Zhong, Junpei</creatorcontrib><creatorcontrib>Li, Weihua</creatorcontrib><title>Pyramidal Predictive Network: A Model for Visual-frame Prediction Based on Predictive Coding Theory</title><title>arXiv.org</title><description>Visual-frame prediction is a pixel-dense prediction task that infers future frames from past frames. Lacking of appearance details, low prediction accuracy and high computational overhead are still major problems with current models or methods. In this paper, we propose a novel neural network model inspired by the well-known predictive coding theory to deal with the problems. Predictive coding provides an interesting and reliable computational framework, which will be combined with other theories such as the cerebral cortex at different level oscillates at different frequencies, to design an efficient and reliable predictive network model for visual-frame prediction. Specifically, the model is composed of a series of recurrent and convolutional units forming the top-down and bottom-up streams, respectively. The update frequency of neural units on each of the layer decreases with the increasing of network levels, which results in neurons of higher-level can capture information in longer time dimensions. According to the experimental results, this model shows better compactness and comparable predictive performance with existing works, implying lower computational cost and higher prediction accuracy. Code is available at https://github.com/Ling-CF/PPNet.</description><subject>Coding theory</subject><subject>Neural networks</subject><subject>Performance prediction</subject><subject>Visual tasks</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNjj0LwjAURYMgWLT_4YFzoSb9dNOiuCgOxbWE5lVTY6NJq_Tf20HE0ekeuIfLHRGHMrbwkoDSCXGtrX3fp1FMw5A5pDz2ht-k4AqOBoUsW_lEOGD70ua6hBXstUAFlTZwkrbjyqsGH7-ybmDNLQoY4Gcg00I2Z8gvqE0_I-OKK4vuJ6dkvt3k2c67G_3o0LZFrTvTDFVB4-FalKRpwP6z3n1QRXg</recordid><startdate>20221115</startdate><enddate>20221115</enddate><creator>Ling, Chaofan</creator><creator>Zhong, Junpei</creator><creator>Li, Weihua</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20221115</creationdate><title>Pyramidal Predictive Network: A Model for Visual-frame Prediction Based on Predictive Coding Theory</title><author>Ling, Chaofan ; Zhong, Junpei ; Li, Weihua</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27026689943</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Coding theory</topic><topic>Neural networks</topic><topic>Performance prediction</topic><topic>Visual tasks</topic><toplevel>online_resources</toplevel><creatorcontrib>Ling, Chaofan</creatorcontrib><creatorcontrib>Zhong, Junpei</creatorcontrib><creatorcontrib>Li, Weihua</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection (ProQuest)</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ling, Chaofan</au><au>Zhong, Junpei</au><au>Li, Weihua</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Pyramidal Predictive Network: A Model for Visual-frame Prediction Based on Predictive Coding Theory</atitle><jtitle>arXiv.org</jtitle><date>2022-11-15</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Visual-frame prediction is a pixel-dense prediction task that infers future frames from past frames. Lacking of appearance details, low prediction accuracy and high computational overhead are still major problems with current models or methods. In this paper, we propose a novel neural network model inspired by the well-known predictive coding theory to deal with the problems. Predictive coding provides an interesting and reliable computational framework, which will be combined with other theories such as the cerebral cortex at different level oscillates at different frequencies, to design an efficient and reliable predictive network model for visual-frame prediction. Specifically, the model is composed of a series of recurrent and convolutional units forming the top-down and bottom-up streams, respectively. The update frequency of neural units on each of the layer decreases with the increasing of network levels, which results in neurons of higher-level can capture information in longer time dimensions. According to the experimental results, this model shows better compactness and comparable predictive performance with existing works, implying lower computational cost and higher prediction accuracy. Code is available at https://github.com/Ling-CF/PPNet.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2022-11
issn 2331-8422
language eng
recordid cdi_proquest_journals_2702668994
source Free E- Journals
subjects Coding theory
Neural networks
Performance prediction
Visual tasks
title Pyramidal Predictive Network: A Model for Visual-frame Prediction Based on Predictive Coding Theory
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-13T08%3A04%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Pyramidal%20Predictive%20Network:%20A%20Model%20for%20Visual-frame%20Prediction%20Based%20on%20Predictive%20Coding%20Theory&rft.jtitle=arXiv.org&rft.au=Ling,%20Chaofan&rft.date=2022-11-15&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2702668994%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2702668994&rft_id=info:pmid/&rfr_iscdi=true