Zum Inhalt springen

Datei:Simplified neural network example.svg

Aus MOOCsWiki Staging
Originaldatei (SVG-Datei, Basisgröße: 1.028 × 882 Pixel, Dateigröße: 71 KB)

Diese Datei stammt aus Wikimedia Commons und kann von anderen Projekten verwendet werden. Die Beschreibung von deren Dateibeschreibungsseite wird unten angezeigt.

Beschreibung

Beschreibung
English: Simplified neural network example for object detection: As seen at the output at right, the network is trained to associate a ringed texture and star outline with a starfish, and a striped texture and oval shape with a sea urchin. In this run, it correctly detects the starfish in the input picture at left. In addition, a shell that was not included in the training gives a weak signal for the oval shape, resulting in a weak signal from only one of two intermediate nodes for the sea urchin output, which may still result in a false positive result (or "hallucination") for sea urchin. In reality, textures and outlines would not be represented by single nodes, but rather by associated weight patterns of multiple nodes.
Datum
Quelle

Eigenes Werk

  • Reference: Ferrie, C., & Kaiser, S. (2019) Neural Networks for Babies, Sourcebooks ISBN: 1492671207.
Urheber
Mikael Häggström, M.D. Author info
- Reusing images
- Conflicts of interest:
  None
Mikael Häggström, M.D.
Andere Versionen
Raster (.png) version

Context

  • Simplified example of training a neural network in object detection: The network is trained by multiple images known to depict starfish and sea urchins, which are correlated with "nodes" representing visual features. Starfish match with a ringed texture and star outline, whereas most sea urchins match with a striped texture and oval shape.
    Simplified example of training a neural network in object detection: The network is trained by multiple images known to depict starfish and sea urchins, which are correlated with "nodes" representing visual features. Starfish match with a ringed texture and star outline, whereas most sea urchins match with a striped texture and oval shape.
  • The resulting model contains weighted associations between visual features and output categories. Because one training image depicts a ring-textured sea urchin, the model also develops a weak association between ringed texture and sea urchin.
    The resulting model contains weighted associations between visual features and output categories. Because one training image depicts a ring-textured sea urchin, the model also develops a weak association between ringed texture and sea urchin.
  • Subsequent run of the model on an input image (left): The network correctly detects the starfish. However, the weak association between ringed texture and sea urchin also gives a weak signal to the latter from one of two intermediate nodes. In addition, a shell not included in the training gives a weak signal for the oval shape, also resulting in a weak signal for the sea urchin output. These weak signals may result in a false positive result for sea urchin.
    Subsequent run of the model on an input image (left): The network correctly detects the starfish. However, the weak association between ringed texture and sea urchin also gives a weak signal to the latter from one of two intermediate nodes. In addition, a shell not included in the training gives a weak signal for the oval shape, also resulting in a weak signal for the sea urchin output. These weak signals may result in a false positive result for sea urchin.

Lizenz

Creative Commons CC-Zero Diese Datei wird unter der Creative-Commons-Lizenz CC0 1.0 Verzicht auf das Copyright zur Verfügung gestellt.
Die Person, die das Werk mit diesem Dokument verbunden hat, übergibt dieses weltweit der Gemeinfreiheit, indem sie alle Urheberrechte und damit verbundenen weiteren Rechte – im Rahmen der jeweils geltenden gesetzlichen Bestimmungen – aufgibt. Das Werk kann – selbst für kommerzielle Zwecke – kopiert, modifiziert und weiterverteilt werden, ohne hierfür um Erlaubnis bitten zu müssen.

Kurzbeschreibungen

Ergänze eine einzeilige Erklärung, was diese Datei darstellt.
Simplified neural network example: The network is trained to associate a ringed pattern and star outline with a sea star, and a striped pattern and oval shape with a sea urchin. In this run, it correctly detects the sea star in the picture at left.

In dieser Datei abgebildete Objekte

Motiv

TensorFlow

Dateiversionen

Klicke auf einen Zeitpunkt, um diese Version zu laden.

Version vomVorschaubildMaßeBenutzerKommentar
aktuell23:52, 2. Okt. 2023Vorschaubild der Version vom 23:52, 2. Okt. 20231.028 × 882 (71 KB)wikimediacommons>Mikael HäggströmUpdate

Metadaten

Diese Datei enthält weitere Informationen, die in der Regel von der Digitalkamera oder dem verwendeten Scanner stammen. Durch nachträgliche Bearbeitung der Originaldatei können einige Details verändert worden sein.

Abgerufen von „https://staging.moocwiki.org/index.php?title=Datei:Simplified_neural_network_example.svg“