Just In
- 55 min ago Best Noise-Cancelling Earbuds Under Rs 5,000: CMF Buds Pro, Redmi Buds 5, Realme Buds Air 5, and More
- 59 min ago How to Get Zomato Gold Membership Worth Rs 999 for Free
- 3 hrs ago Garena Free Fire Max Redeem Codes for April 20, 2024: Get Access to the Latest In-game Loot
- 3 hrs ago Apple Watch X Renders Surface: Magnetic Bands, Blood Pressure Tracking, and More
Don't Miss
- Movies Love, Sex Aur Dhokha 2: The REAL Reason Of Rajkummar Rao And Nushrratt Bharuccha Not Being Part Of The Film
- Finance Gold Prices: 10-Gram 24-Carat Rises Rs 8,010 Before Falling; Chennai Gold Price At Rs 75,110
- Sports DC vs SRH My11Circle Prediction IPL 2024 Match 35: DEL vs HYD Fantasy Tips & Expert Picks
- News Punjab Human Rights Panel Issues Notice To ADGP In Sangrur Jail Clash Case
- Lifestyle Russian Influencer Starves His Newborn To Death With Sunlight Diet, Know Dos And Don’ts Of This Diet
- Education UPMSP Class 10 and 12 Results 2024 Released Today, Check the Details Here
- Automobiles Tesla CEO Elon Musk's Much-Awaited Visit to India Deferred, Leaving Questions Unanswered
- Travel Journey From Delhi To Ooty: Top Transport Options And Attractions
Apple publishes its first paper on artificial intelligence
This Apple paper seem's interesting!
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.
LG G6 Might Feature G5-Like Design
Titled 'Learning from Simulated and Unsupervised Images through Adversarial Training', the paper describes techniques of training computer vision algorithms to recognize 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.
Meizu M5S With Metal Body to Be Unveiled in China Soon
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.
IANS
-
99,999
-
1,29,999
-
69,999
-
41,999
-
64,999
-
99,999
-
29,999
-
63,999
-
39,999
-
1,56,900
-
79,900
-
1,39,900
-
1,29,900
-
65,900
-
1,56,900
-
1,30,990
-
76,990
-
16,499
-
30,700
-
12,999
-
18,800
-
62,425
-
1,15,909
-
93,635
-
75,804
-
9,999
-
11,999
-
3,999
-
2,500
-
3,599