Most image-recognition systems are trained using large databases that contain millions of photos of everyday objects, from snakes to shakes to shoes. With repeated exposure, AIs learn to tell one type of object from another. Now researchers in Japan have shown that AIs can start learning to recognize everyday objects by being trained on computer-generated fractals instead.
Generating training data automatically is an exciting trend in machine learning. And using an endless supply of synthetic images rather than photos scraped from the internet avoids problems with existing hand-crafted data sets. Researchers also tried training their AI using other abstract images, including ones produced using Perlin noise and Bezier curves.
More information: