shot-button
Union Budget Union Budget
Home > Lifestyle News > Health And Fitness News > Article > Apple publishes its first paper on artificial intelligence

Apple publishes its first paper on artificial intelligence

Updated on: 27 December,2016 02:02 PM IST  | 
IANS |

Breaking with its tradition of keeping research topics a secret, Apple has come out in the open, publishing its first artificial intelligence (AI) research paper that focuses on advanced image recognition

Apple publishes its first paper on artificial intelligence

Listen to this article
Apple publishes its first paper on artificial intelligence
x
00:00

Apple publishes its first paper on artificial intelligence

New York: Breaking with its tradition of keeping research topics a secret, Apple has come out in the open, publishing its first artificial intelligence (AI) research paper that focuses on advanced image recognition.


Apple's first public research paper on AI was penned by vision expert Ashish Shrivastava and a team of engineers including Tomas Pfister, Oncel Tuzel, Wenda Wang, Russ Webb and Apple Director of Artificial Intelligence Research Josh Susskind, appleinsider.com reported on Tuesday. Shrivastava holds a PhD in computer vision from the University of Maryland.



Titled 'Learning from Simulated and Unsupervised Images through Adversarial Training', the paper describes techniques of training computer vision algorithms to recognise objects using synthetic, or computer generated, images. However, learning from synthetic images may not achieve the desired performance owing to a gap between synthetic and real image distributions.

To reduce this gap, Apple has proposed Simulated plus Unsupervised (S+U) learning, where the task is to learn a model to improve the realism of a simulator's output using unlabeled real data while preserving the annotation information from the simulator. The company has developed a method for S+U learning that uses an adversarial network similar to Generative Adversarial Networks (GANs), but with synthetic images as inputs instead of random vectors.

The improved realism enables the training of better machine-learning models on large datasets without any data collection or human annotation effort. Moreover, since machine learning models can be sensitive to artifacts in the synthetic data, S+U learning should generate images without artifacts.

"Apple's first public research paper was penned by vision expert Ashish Shrivastava and a team of engineers including Tomas Pfister, Oncel Tuzel, Wenda Wang, Russ Webb and Apple Director of Artificial Intelligence Research Josh Susskind," the report added.

"Exciting news! Mid-day is now on WhatsApp Channels Subscribe today by clicking the link and stay updated with the latest news!" Click here!

Did you find this article helpful?

Yes
No

Help us improve further by providing more detailed feedback and stand a chance to win a 3-month e-paper subscription! Click Here

Note: Winners will be selected via a lucky draw.

Help us improve further by providing more detailed feedback and stand a chance to win a 3-month e-paper subscription! Click Here

Note: Winners will be selected via a lucky draw.


Mid-Day Web Stories

Mid-Day Web Stories

This website uses cookie or similar technologies, to enhance your browsing experience and provide personalised recommendations. By continuing to use our website, you agree to our Privacy Policy and Cookie Policy. OK