Just In
- 12 min ago Honeywell Trueno U5100 Review: Quality Audio Meets Comfortable Design at an Oh-So Reasonable Price
- 20 min ago Sennheiser Momentum True Wireless 4 Earbuds Launched in India: Check Price, Features, Availability
- 34 min ago JioCinema Ad-Free Premium Plans Announced Starting at Rs 29
- 1 hr ago Garena Free Fire Max Redeem Codes for April 25, 2024: Get Access to the Latest Freebies in the Game
Don't Miss
- Education UPSC CAPF 2024 registration begins; Apply online for 506 Assistant Commandant posts, Know more
- Automobiles Gujarat Targets Unauthorized White Headlights To Boost Road Safety
- News 417 Out of 1192 Candidates In Phase 2 Of Polls Face Criminal Cases, Most From BJP: ADR Data
- Movies Kashmera On Welcoming Govinda At Arti Singh’s Wedding: He Might Have A Problem With Me & Krushna But…
- Sports 103 Not Out: S Ramdas - 103-year-old CSK fan fondly called 'Senior Valiban' - aspires to meet MS Dhoni
- Finance Rs 44,000 Crore M-Cap Lost, Stock Falls 10%, No More 4th Largest Bank; How RBI's Ban Rocked Kotak
- Lifestyle Exclusive: On World Malaria Day 2024, Dr Shares Danger Signs Parents Must Watch Out For In Child With Malaria
- Travel Escape to Kalimpong, Gangtok, and Darjeeling with IRCTC's Tour Package; Check Itinerary
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
-
11,999
-
16,026
-
14,248
-
14,466
-
26,634
-
18,800
-
62,425
-
1,15,909
-
93,635
-
75,804