<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.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>2026-11-22T21:03:26Z</responseDate><request verb="GetRecord" identifier="oai:uwspace.uwaterloo.ca:10012/17103" metadataPrefix="dim">https://dspacemainprd01.lib.uwaterloo.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:uwspace.uwaterloo.ca:10012/17103</identifier><datestamp>2025-03-26T23:33:02Z</datestamp><setSpec>com_10012_9924</setSpec><setSpec>com_10012_1</setSpec><setSpec>col_10012_9934</setSpec><setSpec>col_10012_6</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:doc="http://www.lyncode.com/xoai" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Schonlau, Matthias</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author" authority="31e3bc92-55cf-40fd-b2ea-27caf39efc5a" confidence="600">Sucholutsky, Ilia</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2021-06-15T18:16:46Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2021-06-15T18:16:46Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2021-06-15</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2021-06-09</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/10012/17103</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en">The tremendous recent growth in the fields of artificial intelligence and machine learning has largely been tied to the availability of big data and massive amounts of compute. The increasingly popular approach of training large neural networks on large datasets has provided great returns, but it leaves behind the multitude of researchers, companies, and practitioners who do not have access to sufficient funding, compute power, or volume of data. This thesis aims to rectify this growing imbalance by probing the limits of what machine learning and deep learning methods can achieve with small data.  &#xd;
&#xd;
What knowledge does a dataset contain? At the highest level, a dataset is just a collection of samples: images, text, etc. Yet somehow, when we train models on these datasets, they are able to find patterns, make inferences, detect similarities, and otherwise generalize to samples that they have previously never seen. This suggests that datasets may contain some kind of intrinsic knowledge about the systems or distributions from which they are sampled. Moreover, it appears that this knowledge is somehow distributed and duplicated across the samples; we intuitively expect that removing an image from a large training set will have virtually no impact on the final model performance. &#xd;
&#xd;
We develop a framework to explain efficient generalization around three principles: information sharing, information repackaging, and information injection. We use this framework to propose `less than one&amp;apos;-shot learning, an extreme form of few-shot learning where a learner must recognize N classes from M &amp;lt; N training examples. To achieve this extreme level of efficiency, we develop new framework-consistent methods and theory for lost data restoration, for dataset size reduction, and for few-shot learning with deep neural networks and other popular machine learning models.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en">en</dim:field>
   <dim:field mdschema="dc" element="publisher" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="dc" element="relation" qualifier="uri" lang="en">https://github.com/ilia10000/dataset-distillation</dim:field>
   <dim:field mdschema="dc" element="relation" qualifier="uri" lang="en">https://github.com/ilia10000/LO-Shot</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">deep learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">machine learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">few-shot learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">one-shot learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">dataset reduction</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">dataset distillation</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">small data</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">ML</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">AI</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">artificial intelligence</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">neural networks</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">NLP</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">computer vision</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">optimization</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">LO-shot learning</dim:field>
   <dim:field mdschema="dc" element="title" lang="en">Learning From Almost No Data</dim:field>
   <dim:field mdschema="dc" element="type" lang="en">Doctoral Thesis</dim:field>
   <dim:field mdschema="dc" element="pending">false</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="department" lang="en">Statistics and Actuarial Science</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="discipline" lang="en">Statistics</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="grantor" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="uws-etd" element="degree" lang="en">Doctor of Philosophy</dim:field>
   <dim:field mdschema="uws-etd" element="embargo" qualifier="terms" lang="en">0</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="advisor">Schonlau, Matthias</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="affiliation1" lang="en">Faculty of Mathematics</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="city" lang="en">Waterloo</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="country" lang="en">Canada</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="province" lang="en">Ontario</dim:field>
   <dim:field mdschema="uws" element="typeOfResource" lang="en">Text</dim:field>
   <dim:field mdschema="uws" element="peerReviewStatus" lang="en">Unreviewed</dim:field>
   <dim:field mdschema="uws" element="scholarLevel" lang="en">Graduate</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>