Humans can predict how machines (mis)classify adversarial images

Join Transform 2021 for the most important themes in enterprise AI & Data. Learn more. One of the frustrations with machine learning, particularly in the area of image recognition, is that neural nets sometimes get things completely, laughably, inexplicably wrong. We question how an AI could be fed an image of an unmistakably dog-like dog … Continue reading Humans can predict how machines (mis)classify adversarial images