ОписSimplified neural network training example.svg
English: Simplified example of training a neural network in object detection: The network is trained by multiple images that are known to depict starfish and sea urchins, which are correlated with "nodes" that represent visual aspects, in this case texture and outline. 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 shaped sea urchin creates a weakly weighted association between them.
Simplified example of training a neural network in object detection: The network is trained by multiple images that are known to depict starfish and sea urchins, which are correlated with "nodes" that represent visual features. 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.
Subsequent run of the network on an input image (left): 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 sea urchin.
Особа која је учествовало у раду на овом документу посветила је дело јавном власништву, одричући се свих права на то дело широм света, по закону о ауторским правима и повезаним или сродним законским правима које би имао/имала, у мери дозвољеној законом. Можете да умножавате, мењате, расподељујете и прилагођавате дело, чак и у комерцијалне сврхе, без тражења дозволе.
http://creativecommons.org/publicdomain/zero/1.0/deed.enCC0Creative Commons Zero, Public Domain Dedicationfalsefalse