<?xml version='1.0' encoding='UTF-8'?><?xml-stylesheet href='static/style.xsl' type='text/xsl'?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-22T09:32:11Z</responseDate><request verb="GetRecord" identifier="oai:ecommons.cornell.edu:1813/44294" metadataPrefix="dim">https://ecommons.cornell.edu/server/oai/request</request><GetRecord><record><header><identifier>oai:ecommons.cornell.edu:1813/44294</identifier><datestamp>2026-05-14T13:56:29Z</datestamp><setSpec>com_1813_35</setSpec><setSpec>col_1813_47</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="author">Sedra, Daniel</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="chair">Weinberger,Kilian Quirin</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="committeeMember">Van Loan,Charles Francis</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2016-07-05T15:30:01Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2021-05-30T06:00:14Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2016-05-29</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/1813/44294</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="doi">https://doi.org/10.7298/X44B2Z7F</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="bibid">9597056</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract">Convolutional networks are the current state of the art for image tasks. It has long been known that depth is key for increasing their expressive power, but many challenges rendered training difficult. With the advent of deep residual networks [13], the feasible depth of networks has increased from a few dozen to several hundred. Nevertheless several traditional machine learning problems persist such as overfitting, vanishing gradients, and diminishing feature reuse. Additionally, the training time for large networks is still measured in weeks. This thesis will detail two novel approaches for training deep residual networks that address the aforementioned persistent difficulties and present experimental evidence of their efficacy.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso">en_US</dim:field>
   <dim:field mdschema="dc" element="subject">deep learning</dim:field>
   <dim:field mdschema="dc" element="subject">machine learning</dim:field>
   <dim:field mdschema="dc" element="subject">deep residual networks</dim:field>
   <dim:field mdschema="dc" element="title">Training Paradigms For Deep Residual Networks</dim:field>
   <dim:field mdschema="dc" element="type">dissertation or thesis</dim:field>
   <dim:field mdschema="dc" element="format" qualifier="mimetype">application/pdf</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="discipline">Computer Science</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="grantor">Cornell University</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="level">Master of Science</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="name">M.S., Computer Science</dim:field>
   <dim:field mdschema="dspace" element="entity" qualifier="type">Publication</dim:field>
   <dim:field mdschema="cris" element="virtual" qualifier="collection" authority="https://cornell-ecommons.eks.prod.4science.cloud/handle/1813/47" confidence="600">Cornell Theses and Dissertations</dim:field>
   <dim:field mdschema="cris" element="virtual" qualifier="author">Sedra, Daniel</dim:field>
   <dim:field mdschema="cris" element="virtualsource" qualifier="collection">5893a6ea-7af3-41d7-abc6-04bcd26ab5df</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
   <dim:field mdschema="cerif" element="openaire" authority="" confidence="-1">&lt;Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="131bd338-e9b4-4181-8617-dec1e7ae5eb9">
	&lt;Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843&lt;/Type>
	&lt;Language>en_US&lt;/Language>
   	&lt;Title>Training Paradigms For Deep Residual Networks&lt;/Title>
   	&lt;PublishedIn>
    	&lt;Publication>
      	&lt;/Publication>
   	&lt;/PublishedIn>
   	&lt;PublicationDate>2016-05-29&lt;/PublicationDate>
   	&lt;DOI>https://doi.org/10.7298/X44B2Z7F&lt;/DOI>
   	&lt;Authors>
      	&lt;Author>
        	&lt;DisplayName>Sedra, Daniel&lt;/DisplayName>
         	&lt;Affiliation>
         		&lt;OrgUnit>
         		&lt;/OrgUnit>
         	&lt;/Affiliation>
      	&lt;/Author>
	&lt;/Authors>
   	&lt;Editors>
	&lt;/Editors>
    &lt;Publishers>
        &lt;Publisher>
            &lt;OrgUnit />
        &lt;/Publisher>
    &lt;/Publishers>
    &lt;Keyword>deep learning&lt;/Keyword>
    &lt;Keyword>machine learning&lt;/Keyword>
    &lt;Keyword>deep residual networks&lt;/Keyword>
   	&lt;Abstract>Convolutional networks are the current state of the art for image tasks. It has long been known that depth is key for increasing their expressive power, but many challenges rendered training difficult. With the advent of deep residual networks [13], the feasible depth of networks has increased from a few dozen to several hundred. Nevertheless several traditional machine learning problems persist such as overfitting, vanishing gradients, and diminishing feature reuse. Additionally, the training time for large networks is still measured in weeks. This thesis will detail two novel approaches for training deep residual networks that address the aforementioned persistent difficulties and present experimental evidence of their efficacy.&lt;/Abstract>
	&lt;Access xmlns="http://purl.org/coar/access_right" 
    >
    &lt;/Access>
&lt;/Publication>
</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>