Uber creates AI to generate data for training other AI models

Generative adversarial networks (GANs) -- two-part AI systems consisting of generators that create samples and discriminators that attempt to distinguish between the generated samples and real-world samples -- have countless uses, and one of them is producing synthetic data. Researchers at Uber recently leveraged this in a paper titled "Accelerating Neural Architecture Search by Learning," which proposes a tailored GAN -- Generative Teaching Networks (GTNs) -- that generates data or training environments from which a model learns before being tested on a target task. They say that they speed up searches for algorithms by up to nine times compared with approaches that use real data alone, and that GTNs are competitive with state-of-the-art architectures that achieve top performance while using "orders of magnitude" less computation. As the contributing authors explain in a blog post, most model searches require "substantial" resources because they evaluate models by training them on a data set until their performance no longer improves. This process might be repeated for thousands or more model architectures in a single cycle, which is both expensive in terms of computation and incredibly time-consuming.