Further proving their deep interest in machine learning, Apple have launched the "Apple Machine Learning Journal".
As they put it:
Welcome to the Apple Machine Learning Journal. Here, you can read posts written by Apple engineers about their work using machine learning technologies to help build innovative products for millions of people around the world.
They’ve kicked it off with ‘Vol. 1, Issue 1’, titled "Improving the Realism of Synthetic Images":
Most successful examples of neural nets today are trained with supervision. However, to achieve high accuracy, the training sets need to be large, diverse, and accurately annotated, which is costly. An alternative to labelling huge amounts of data is to use synthetic images from a simulator. This is cheap as there is no labeling cost, but the synthetic images may not be realistic enough, resulting in poor generalization on real test images. To help close this performance gap, we’ve developed a method for refining synthetic images to make them look more realistic. We show that training models on these refined images leads to significant improvements in accuracy on various machine learning tasks.
I can imagine the content being well over my head, but I’m going to enjoy keeping up with it.