Top Page | English | 简体中文 | 繁體中文 | 한국어 | 日本語
Tuesday, 12 December 2017, 19:31 HKT/SGT
Share:
    

Source: NEC Corporation
NEC Develops Deep Learning Technology to Improve Recognition Accuracy

TOKYO, Dec 12, 2017 - (JCN Newswire) - NEC Corporation (TSE: 6701) today announced it has developed automatic optimization technology for deep learning in order to facilitate improvements in recognition accuracy.

In recent years, there have been tremendous advances in deep learning, which is now contributing to image recognition, speech recognition, and a wide range of other fields. Deep learning enables higher levels of recognition accuracy by capitalizing on the deeply layered structures of artificial neural networks in order to learn from prepared data.

If systems become excessively familiar with data however, they become unable to accurately recognize data that they have not learned. This is known as "overtraining," and results in degradation of recognition accuracy when dealing with data that was not used in the learning process. To prevent overtraining, "regularization" technology is commonly used, which regulates the extent of learning to prevent it from reaching an excessive degree.

"This technology predicts the progress of learning at every layer based on the structure of an artificial neural network, and enables regularization to be automatically configured accordingly," said Akio Yamada, General Manager of NEC's Data Science Research Laboratories. "This means that learning is optimized across the entire network, making it possible to improve recognition accuracy, such as reducing recognition errors by around 20% when compared to conventional systems."

"This technology is expected to improve recognition accuracy for image and speech recognition, and a whole host of other fields in which deep learning is used," continues Yamada. "It will be able to improve the accuracy of facial recognition and behavior analysis for purposes that include video surveillance, for instance, or to increase the efficiency of inspections of infrastructure, or enable the automatic detection of system failures, accidents or disasters."


Contact:
NEC 
Seiichiro Toda         
s-toda@cj.jp.nec.com 
+81-3-3798-6511


Topic: Press release summary
Source: NEC Corporation

Sectors: CyberSecurity
http://www.acnnewswire.com
From the Asia Corporate News Network


Copyright © 2025 ACN Newswire. All rights reserved. A division of Asia Corporate News Network.


NEC Corporation Links

http://www.nec.com

https://www.facebook.com/nec.global/

https://twitter.com/NEC_corp

https://www.youtube.com/user/NECglobalOfficial

https://www.linkedin.com/company/nec/

NEC Corporation
Sept 5, 2025 10:20 HKT/SGT
NEC participates in Locked Shields 2025 hosted by the NATO Cooperative Cyber Defence Centre of Excellence
Sept 4, 2025 10:15 HKT/SGT
NEC to begin proof of concept for early earthquake detection and analysis in Colombia
Aug 27, 2025 21:57 HKT/SGT
NEC develops AI technology for digitalizing work tasks without the need for pre-training and utilizing video from multiple cameras covering wide area worksites
Aug 25, 2025 16:30 HKT/SGT
NEC technology predicts sudden traffic congestion in real time using optical fiber cables
Aug 21, 2025 19:32 HKT/SGT
NEC digital technologies to empower small-scale producers in Africa in partnership with IFAD
Aug 21, 2025 18:27 HKT/SGT
NEC signs Memorandum of Cooperation with the Senegalese government, CFPT-SJ, JICA, and four Japan-based companies for vocational training in Senegal
Aug 21, 2025 09:39 HKT/SGT
NEC develops robot control technology using AI to achieve safe, efficient autonomous movement even at sites with many obstacles
Aug 20, 2025 14:53 HKT/SGT
NEC collaborates with WFP to strengthen cooperative development in Africa
Aug 19, 2025 10:33 HKT/SGT
NEC and ClimateAi Develop Conceptual Model to Promote Climate Change Adaptation in Agriculture
Aug 18, 2025 13:38 HKT/SGT
UNFPA and NEC Collaborate to Build Beneficiary Information Management and e-Voucher System
More news >>
 News Alerts
Copyright © 2025 ACN Newswire - Asia Corporate News Network
Home | About us | Services | Partners | Events | Login | Contact us | Privacy Policy | Terms of Use | RSS
US: +1 214 890 4418 | China: +86 181 2376 3721 | Hong Kong: +852 8192 4922 | Singapore: +65 6549 7068 | Tokyo: +81 3 6859 8575

Connect With us: