@inproceedings{dharmaretnam-fyshe-2018-emergence,
title = "The Emergence of Semantics in Neural Network Representations of Visual Information",
author = "Dharmaretnam, Dhanush and
Fyshe, Alona",
editor = "Walker, Marilyn and
Ji, Heng and
Stent, Amanda",
booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N18-2122",
doi = "10.18653/v1/N18-2122",
pages = "776--780",
abstract = "Word vector models learn about semantics through corpora. Convolutional Neural Networks (CNNs) can learn about semantics through images. At the most abstract level, some of the information in these models must be shared, as they model the same real-world phenomena. Here we employ techniques previously used to detect semantic representations in the human brain to detect semantic representations in CNNs. We show the accumulation of semantic information in the layers of the CNN, and discover that, for misclassified images, the correct class can be recovered in intermediate layers of a CNN.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dharmaretnam-fyshe-2018-emergence">
<titleInfo>
<title>The Emergence of Semantics in Neural Network Representations of Visual Information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dhanush</namePart>
<namePart type="family">Dharmaretnam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alona</namePart>
<namePart type="family">Fyshe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marilyn</namePart>
<namePart type="family">Walker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Stent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans, Louisiana</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Word vector models learn about semantics through corpora. Convolutional Neural Networks (CNNs) can learn about semantics through images. At the most abstract level, some of the information in these models must be shared, as they model the same real-world phenomena. Here we employ techniques previously used to detect semantic representations in the human brain to detect semantic representations in CNNs. We show the accumulation of semantic information in the layers of the CNN, and discover that, for misclassified images, the correct class can be recovered in intermediate layers of a CNN.</abstract>
<identifier type="citekey">dharmaretnam-fyshe-2018-emergence</identifier>
<identifier type="doi">10.18653/v1/N18-2122</identifier>
<location>
<url>https://aclanthology.org/N18-2122</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>776</start>
<end>780</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Emergence of Semantics in Neural Network Representations of Visual Information
%A Dharmaretnam, Dhanush
%A Fyshe, Alona
%Y Walker, Marilyn
%Y Ji, Heng
%Y Stent, Amanda
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F dharmaretnam-fyshe-2018-emergence
%X Word vector models learn about semantics through corpora. Convolutional Neural Networks (CNNs) can learn about semantics through images. At the most abstract level, some of the information in these models must be shared, as they model the same real-world phenomena. Here we employ techniques previously used to detect semantic representations in the human brain to detect semantic representations in CNNs. We show the accumulation of semantic information in the layers of the CNN, and discover that, for misclassified images, the correct class can be recovered in intermediate layers of a CNN.
%R 10.18653/v1/N18-2122
%U https://aclanthology.org/N18-2122
%U https://doi.org/10.18653/v1/N18-2122
%P 776-780
Markdown (Informal)
[The Emergence of Semantics in Neural Network Representations of Visual Information](https://aclanthology.org/N18-2122) (Dharmaretnam & Fyshe, NAACL 2018)
ACL