| dbo:description
|
- 人工知能（AI）が事実に基づかない情報を生成する現象 (ja)
- réponse manifestement fausse d'une intelligence artificielle (fr)
- fałszywe informacje generowane przez sztuczną inteligencję podawane jakby były prawdziwe (pl)
- confident unjustified claim by an AI (en)
- الردود والإجابات الواثقة التي تُقدّمها أنظمة الذكاء الاصطناعي على اختلافها والتي لا مصدر لها ضمنَ بيانات التدريب التي خضعت لها (ar)
- resposta confiante de IA não justificada (pt)
- alegación segura pero injustificada por parte de una IA (es)
- odziv, ki ga ustvari umetna inteligenca in vsebuje napačne ali zavajajoče informacije, predstavljene kot dejstva (sl)
- überzeugend formuliertes aber falsches KI-Resultat (de)
- és una resposta segura d'una IA que no sembla estar justificada per les seves dades d'entrenament. (ca)
- 인공지능의 환각 (ko)
|
| dbo:thumbnail
| |
| dbp:caption
|
- The images above demonstrate an example of how an artificial neural network might make a false positive result in object detection. The input image is a simplified example of the training phase, using multiple images that are known to depict starfish and sea urchins, respectively. The starfish match with a ringed texture and a star outline, whereas most sea urchins match with a striped texture and oval shape. However, the instance of a ring textured sea urchin creates a weakly weighted association between them. (en)
- Subsequent run of the network on an input image : The network correctly detects the starfish. However, the weakly weighted association between ringed texture and sea urchin also confers a weak signal to the latter from one of two intermediate nodes. In addition, a shell that was 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 the presence of a sea urchin although there was none in the input image.
In reality, textures and outlines would not be represented by single nodes, but rather by associated weight patterns of multiple nodes. (en)
|
| dbp:direction
| |
| dbp:image
|
- Simplified neural network example.svg (en)
- Simplified neural network training example.svg (en)
|
| dbp:totalWidth
| |
| dbp:wikiPageUsesTemplate
| |
| dct:subject
| |
| rdf:type
| |
| rdfs:label
|
- Hallucination (artificial intelligence) (en)
|
| owl:differentFrom
| |
| prov:wasDerivedFrom
| |
| foaf:depiction
| |
| foaf:isPrimaryTopicOf
| |
| is rdfs:seeAlso
of | |
| is owl:differentFrom
of | |
| is foaf:primaryTopic
of | |
