Information theoretic and machine learning approaches to quantify non-linear visual feature interaction underlying visual object recognition

Information theoretic and machine learning approaches to quantify non-linear visual feature interaction underlying visual object recognition

Bibliographic Details
Main Authors: Alemi-Neissi Alireza, Baldassi Carlo, Braunstein Alfredo, Pagnani Andrea, Zecchina Riccardo, Zoccolan Davide
Format: Article
Language:English
Published: BMC 2012-07-01
Series:BMC Neuroscience
id doaj-99b5a312d9364487a89b011c75b8b004
record_format Article
spelling doaj-99b5a312d9364487a89b011c75b8b0042020-11-24T20:41:26ZengBMCBMC Neuroscience1471-22022012-07-0113Suppl 1P210.1186/1471-2202-13-S1-P2Information theoretic and machine learning approaches to quantify non-linear visual feature interaction underlying visual object recognitionAlemi-Neissi AlirezaBaldassi CarloBraunstein AlfredoPagnani AndreaZecchina RiccardoZoccolan Davide
collection DOAJ
language English
format Article
sources DOAJ
author Alemi-Neissi Alireza
Baldassi Carlo
Braunstein Alfredo
Pagnani Andrea
Zecchina Riccardo
Zoccolan Davide
spellingShingle Alemi-Neissi Alireza
Baldassi Carlo
Braunstein Alfredo
Pagnani Andrea
Zecchina Riccardo
Zoccolan Davide
Information theoretic and machine learning approaches to quantify non-linear visual feature interaction underlying visual object recognition
BMC Neuroscience
author_facet Alemi-Neissi Alireza
Baldassi Carlo
Braunstein Alfredo
Pagnani Andrea
Zecchina Riccardo
Zoccolan Davide
author_sort Alemi-Neissi Alireza
title Information theoretic and machine learning approaches to quantify non-linear visual feature interaction underlying visual object recognition
title_short Information theoretic and machine learning approaches to quantify non-linear visual feature interaction underlying visual object recognition
title_full Information theoretic and machine learning approaches to quantify non-linear visual feature interaction underlying visual object recognition
title_fullStr Information theoretic and machine learning approaches to quantify non-linear visual feature interaction underlying visual object recognition
title_full_unstemmed Information theoretic and machine learning approaches to quantify non-linear visual feature interaction underlying visual object recognition
title_sort information theoretic and machine learning approaches to quantify non-linear visual feature interaction underlying visual object recognition
publisher BMC
series BMC Neuroscience
issn 1471-2202
publishDate 2012-07-01
work_keys_str_mv AT alemineissialireza informationtheoreticandmachinelearningapproachestoquantifynonlinearvisualfeatureinteractionunderlyingvisualobjectrecognition
AT baldassicarlo informationtheoreticandmachinelearningapproachestoquantifynonlinearvisualfeatureinteractionunderlyingvisualobjectrecognition
AT braunsteinalfredo informationtheoreticandmachinelearningapproachestoquantifynonlinearvisualfeatureinteractionunderlyingvisualobjectrecognition
AT pagnaniandrea informationtheoreticandmachinelearningapproachestoquantifynonlinearvisualfeatureinteractionunderlyingvisualobjectrecognition
AT zecchinariccardo informationtheoreticandmachinelearningapproachestoquantifynonlinearvisualfeatureinteractionunderlyingvisualobjectrecognition
AT zoccolandavide informationtheoreticandmachinelearningapproachestoquantifynonlinearvisualfeatureinteractionunderlyingvisualobjectrecognition
_version_ 1716825091968335872

Similar Items