Apple’s AI Team Publishes First Research Paper

Earlier this month, Apple announced that it would allow its artificial intelligence researchers to publish research papers — a major shift in the notoriously secretive company’s policy. Now, just a few weeks later, the first of these papers has been made public on the preprint server arXiv.

The paper — titled “Learning from Simulated and Unsupervised Images through Adversarial Training”— deals with intelligent image recognition technology. Specifically, it describes a technique that would enable a program to recognize and decipher computer-generated images.

So far, this has not been possible because, as the researchers from Apple note, “synthetic data is often not realistic enough,” and increasing the realism is “computationally expensive.”

“With recent progress in graphics, it has become more tractable to train models on synthetic images, potentially avoiding the need for expensive annotations. However, learning from synthetic images may not achieve the desired performance due to a gap between synthetic and real image distributions,” the researchers wrote. “In this paper, we propose Simulated+Unsupervised (S+U) learning, where the goal is to improve the realism of synthetic images from a simulator using unlabeled real data.”

In order to do so, the researchers used a technique known as adversarial learning, wherein two competing neural networks basically try to outsmart each other. In this case, the two neural networks are the generator, which, as the name suggests, generates realistic images, and the discriminator, whose function is to distinguish between generated and real images.

“We develop a method for S+U learning, which we term SimGAN, that refines synthetic images from a simulator using a neural network which we call the ‘refiner network,’” the researchers wrote in the study. “To add realism – the first requirement of an S+U learning algorithm – we train our refiner network using an adversarial loss.”

The paper is likely to be the first of many to be authored and published by Apple’s machine learning researchers in the coming weeks and months, now that the tech giant has lifted its restrictions on sharing research. Reports suggest that this decision was taken primarily to recover the ground Apple has lost in recent years to the likes of Google, Microsoft, Facebook and the Elon Musk-backed startup OpenAI, insofar as AI-related research is concerned.

___

Avaneesh Pandey

Leave a Reply

Latest

“Men in Black” and “Shaft”, sequel duel on the card

 Los Angeles, .- The billboard will live this weekend a duel of sequels with the premieres of the new installments of "Men in Black"...

American McGirt and Canadian Hughes Lead The Players

American William McGirt and Canadian Mackenzie Hughes lead the Players tournament, considered the fifth "big" of the golf season, after completing the first exit...

WHY CONGRESS IS BECOMING MORE POLARIZED AND PARALYZED

By Oliver Harris | You would not think that a lizard is responsible for this. But let me explain. A congressional district is the best way...

The health of Maradona again awakes uncertainty after video on the networks

To 12 days of turning 58 years, the health of the Argentinean Diego Armando Maradona has returned to wake up uncertainty after a video...

Mark Hamill regrets his criticism of Luke Skywalker’s “Star Wars: The Last Jedi”

Actor Mark Hamill, who plays Luke Skywalker in "Star Wars," apologized on Twitter today for his criticism of the new direction his character had...
%d bloggers like this: