Fooling deep neural networks for object detection with adversarial 3-D logos

Over the past decade, researchers have developed a growing number of deep neural networks that can be trained to complete a variety of tasks, including recognizing people or objects in images. While many of these computational techniques have achieved remarkable results, they can sometimes be fooled into misclassifying data.

from News on Artificial Intelligence and Machine Learning https://ift.tt/2XeCkfU

SHARE SHARE SHARE