References

The thesis bibliography in its scientific context

The thesis draws on 88 references and three image sources. The keys match the bibliography in the PDF so every citation in the text can be looked up. Almost all sources are online documents accessed on 7 March 2019 – some are no longer available; the links point to the address cited at the time.

Scientific context

Backpropagation (Rumelhart, Hinton & Williams, 1986)

“Learning representations by back-propagating errors” in Nature is the foundation for training multi-layer networks. Chapter 4 derives the delta rule and the backpropagation algorithm from it, which OCR methods rely on as well.

Hebbian rule (Hebb, 1949)

“The Organization of Behavior” provides the oldest learning rule for artificial neurons: connections between simultaneously active units are strengthened. In the thesis it is the starting point for the overview of learning rules.

COSIMIR model (University of Hildesheim)

The Cognitive Similarity Learning in Information Retrieval model shows how a neural network can learn similarity between query and document – the bridge from chapter 4 to the use of neural networks in retrieval.

Recall and precision

The classic quality measures of information retrieval rate how complete and how accurate a system's answers are. Chapter 3.2 uses them to assess the prototype's search success.

Crawlers, robots.txt and the big bots

Googlebot, Slurp and Bingbot are compared using vendor documentation. From this the thesis derives how the project's own crawler should behave towards websites.

All references

88 of 88 references

Search engines & crawlers 30

  • Bing1

    Bing Webmaster Help: Meet our crawlers

    bing.com · accessed 7 March 2019

  • Google1

    Google Support: Der Googlebot

    support.google.com · accessed 7 March 2019

  • Google2

    Google Support: Google-Crawler (User-Agents)

    support.google.com · accessed 7 March 2019

  • Google3

    Google Support: Index

    support.google.com · accessed 7 March 2019

  • Google4

    Google Support: Crawling-Frequenz

    support.google.com · accessed 7 March 2019

  • Google5

    Google Support: robots.txt

    support.google.com · accessed 7 March 2019

  • Google6

    Google Support: APIs-Google User-Agent

    support.google.com · accessed 7 March 2019

  • Google7

    Google Support: AdSense-Crawler

    support.google.com · accessed 7 March 2019

  • Google8

    Google Support: Duplizierter Content

    support.google.com · accessed 7 March 2019

  • Google9

    Google Support: Richtlinien für Webmaster

    support.google.com · accessed 7 March 2019

  • Heise1

    heise online: Yahoo macht Altavista dicht

    heise.de · accessed 7 March 2019

  • IRWiki1

    Information Retrieval Wiki (University of Glasgow): Crawler

    ir.dcs.gla.ac.uk · accessed 7 March 2019

  • LP1

    luna-park: Suchmaschinen-Marktanteile weltweit 2017

    luna-park.de · accessed 7 March 2019

  • NetPlanet1

    NetPlanet: Archie

    netplanet.org · accessed 7 March 2019

  • NLSEO1

    NextLevelSEO: Was sind Meta Tags?

    nextlevelseo.de · accessed 7 March 2019

  • ORF1

    ORF: Yahoo! übernimmt AltaVista

    orf.at · accessed 7 March 2019

  • Quaero1

    Quaero – europäisches Suchmaschinenprojekt

    quaero.org · accessed 7 March 2019

  • RyteWiki1

    Ryte Wiki: Yahoo! Slurp

    de.ryte.com · accessed 7 March 2019

  • RyteWiki2

    Ryte Wiki: Bingbot

    de.ryte.com · accessed 7 March 2019

  • RyteWiki3

    Ryte Wiki: Duplicate Content

    de.ryte.com · accessed 7 March 2019

  • RyteWiki4

    Ryte Wiki: OnPage-Optimierung

    de.ryte.com · accessed 7 March 2019

  • RyteWiki5

    Ryte Wiki: OffPage-Optimierung

    de.ryte.com · accessed 7 March 2019

  • RyteWiki6

    Ryte Wiki: Ranking

    de.ryte.com · accessed 7 March 2019

  • RyteWiki7

    Ryte Wiki: Hyperlink

    de.ryte.com · accessed 7 March 2019

  • SEL1

    Search Engine Land: What social signals do Google & Bing really count? (Interview von Danny Sullivan)

    searchengineland.com · accessed 7 March 2019

  • SEOChat1

    SEO Chat: The Yahoo! Slurp Crawler

    seochat.com · accessed 7 March 2019

  • SZ1

    Stuttgarter Zeitung: Und am Anfang war nicht Google

    stuttgarter-zeitung.de · accessed 7 March 2019

  • Wik1

    Wiktionary: googeln

    de.wiktionary.org · accessed 7 March 2019

  • Wiki2

    Wikipedia: User Agent

    de.wikipedia.org · accessed 7 March 2019

  • Wiki10

    Wikipedia: Sitemap

    de.wikipedia.org · accessed 7 March 2019

Information retrieval 8

  • FHKOELN1

    FH Köln: Methoden und Verfahren des Information Retrieval

    ixtrieve.fh-koeln.de · accessed 7 March 2019

  • MYSQL1

    MySQL 8.0 Reference Manual: Full-Text Search Functions

    dev.mysql.com · accessed 7 March 2019

  • MYSQL2

    MySQL 8.0 Reference Manual: Natural Language Full-Text Searches

    dev.mysql.com · accessed 7 March 2019

  • ResearchGate

    ResearchGate: Skalierbarkeit von Ontology-Matching-Verfahren

    researchgate.net · accessed 7 March 2019

  • UNIH1

    Universität Hildesheim: Das COSIMIR-Modell für Information Retrieval mit neuronalen Netzen

    pdfs.semanticscholar.org · accessed 7 March 2019

  • Wiki1

    Wikipedia: Information Retrieval

    de.wikipedia.org · accessed 7 March 2019

  • Wiki5

    Wikipedia: Text Retrieval Conference

    de.wikipedia.org · accessed 7 March 2019

  • Wiki7

    Wikipedia: Sequentieller Zugriff

    de.wikipedia.org · accessed 7 March 2019

Neural networks 23

  • Hebb1

    Hebb, D. O.: The Organization of Behavior (S. 62, Übersetzung nach Kandel et al., 1995, S. 700)

    book, no online source · Buch, 1949

  • Na1

    Rumelhart, Hinton, Williams: Learning representations by back-propagating errors (Nature 323, 1986)

    nature.com · accessed 7 March 2019

  • NN1

    neuronalesnetz.de: Einleitung

    neuronalesnetz.de · accessed 7 March 2019

  • NN2

    neuronalesnetz.de: Units

    neuronalesnetz.de · accessed 7 March 2019

  • NN3

    neuronalesnetz.de: Verbindungen zwischen Units

    neuronalesnetz.de · accessed 7 March 2019

  • NN4

    neuronalesnetz.de: Input und Netzinput

    neuronalesnetz.de · accessed 7 March 2019

  • NN5

    neuronalesnetz.de: Aktivitätsfunktion, Aktivitätslevel und Output

    neuronalesnetz.de · accessed 7 March 2019

  • NN6

    neuronalesnetz.de: Trainings- und Testphase

    neuronalesnetz.de · accessed 7 March 2019

  • NN7

    neuronalesnetz.de: Lernregeln – Überblick

    neuronalesnetz.de · accessed 7 March 2019

  • NN8

    neuronalesnetz.de: Hebb-Regel

    neuronalesnetz.de · accessed 7 March 2019

  • NN9

    neuronalesnetz.de: Delta-Regel

    neuronalesnetz.de · accessed 7 March 2019

  • NN10

    neuronalesnetz.de: Backpropagation und folgende

    neuronalesnetz.de · accessed 7 March 2019

  • NN11

    neuronalesnetz.de: Competitive Learning

    neuronalesnetz.de · accessed 7 March 2019

  • NN12

    neuronalesnetz.de: Rekurrente Netze

    neuronalesnetz.de · accessed 7 March 2019

  • NN13

    neuronalesnetz.de: Pattern Associator

    neuronalesnetz.de · accessed 7 March 2019

  • NN14

    neuronalesnetz.de: Netztypen

    neuronalesnetz.de · accessed 7 March 2019

  • NN15

    neuronalesnetz.de: Kompetitive Netze

    neuronalesnetz.de · accessed 7 March 2019

  • NN16

    neuronalesnetz.de: Kohonennetze

    neuronalesnetz.de · accessed 7 March 2019

  • NN17

    neuronalesnetz.de: Probleme

    neuronalesnetz.de · accessed 7 March 2019

  • NN18

    neuronalesnetz.de: Zusammenfassung Lernregeln

    neuronalesnetz.de · accessed 7 March 2019

  • NN19

    neuronalesnetz.de: Zusammenfassung Netztypen

    neuronalesnetz.de · accessed 7 March 2019

  • Wiki3

    Wikipedia: Neuronales Netz

    de.wikipedia.org · accessed 7 March 2019

  • Wiki4

    Wikipedia: Aktionspotential

    de.wikipedia.org · accessed 7 March 2019

Web fundamentals 11

  • FreeForm1

    FreeFormatter.com: MIME Types List

    freeformatter.com · accessed 7 March 2019

  • HTMLSemi1

    HTML-Seminar.de: Textbereiche fett hervorheben mit <b> und <strong>

    html-seminar.de · accessed 7 March 2019

  • HTMLSemi2

    HTML-Seminar.de: Kursiv mit HTML-Befehl <i> oder <em>

    html-seminar.de · accessed 7 March 2019

  • HTMLSemi3

    HTML-Seminar.de: Links

    html-seminar.de · accessed 7 March 2019

  • IANA1

    IANA: Application Media Types (CSV)

    iana.org · accessed 7 March 2019

  • IANA2

    IANA: Media Types

    iana.org · accessed 7 March 2019

  • W3.ORG1

    W3C: The Multipart Content-Type (RFC 1341)

    w3.org · accessed 7 March 2019

  • W3Schools1

    W3Schools: HTML <h1> to <h6> Tags

    w3schools.com · accessed 7 March 2019

  • WebRef1

    WebReference: Relative URLs

    webreference.com · accessed 7 March 2019

  • Wiki8

    Wikipedia: Ajax (Programmierung)

    de.wikipedia.org · accessed 7 March 2019

  • Wiki11

    Wikipedia: Uniform Resource Locator

    de.wikipedia.org · accessed 7 March 2019

Prototype technology 13

Society & privacy 3

  • PH1

    phase-6 Magazin: Der deutsche Wortschatz

    phase-6.de · accessed 7 March 2019

  • Wiki9

    Wikipedia: Spenden

    de.wikipedia.org · accessed 7 March 2019

  • Zeit1

    ZEIT ONLINE: Datenschützer wollen gegen Google vorgehen

    zeit.de · accessed 7 March 2019

Image sources

Three figures in the thesis come from third-party sources and are marked accordingly in the PDF.