Technologies

Will Douglas Heaven has referred to the article "Pre-training without Natural Images,"
proposed by Dr. Hirokatsu Kataoka, a researcher of AIST in Japan, and his collaborators on MIT Technology Review."

"Large datasets like ImageNet have supercharged the last 10 years of AI vision, but they are hard to produce and contain bias. Computer-generated datasets provide an alternative.
...
Now researchers in Japan have shown that AIs can start learning to recognize everyday objects by being trained on computer-generated fractals instead."
...Read more

en
Technologies
1