Apple Publishes Its First Artificial Intelligence Paper
The paper describes a technique for how to improve the training of an algorithm’s ability to recognise images using computer-generated images rather than real-world images.
▻http://www.forbes.com/sites/aarontilley/2016/12/26/apple-publishes-its-first-artificial-intelligence-paper
To improve training with synthetic image data, the paper suggests what the Apple researchers call Simulated+Unsupervised learning, where the realism of a simulated image is boosted. The Apple researchers use a modified version of a new machine learning technique called Generative Adversarial Networks (#GAN), which pits two neural networks against each other and has been used to generate photorealistic images.