NEC Develops Deep Learning Technology to Improve Recognition Accuracy

Dec 12, 2017 20:31 JST

Source: NEC Corporation

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

Source: NEC Corporation
Sectors: CyberSecurity

Related Press Release

NEC Develops High-speed Generative AI Large Language Models (LLM) with World-class Performance

April 24 2024 12:25 JST

NEC Strengthens Commitment to Space Industry with Investment in Seraphim Space Venture Fund II

April 22 2024 14:09 JST

DOCOMO, NTT, NEC and Fujitsu Develop Top-level Sub-terahertz 6G Device Capable of Ultra-high-speed 100 Gbps Transmission

April 11 2024 14:10 JST

Transgene and NEC Present First Clinical Benefits of Neoantigen Cancer Vaccine, TG4050, in Head & Neck Cancer at AACR 2024

April 10 2024 12:36 JST

NEC white paper proposes comprehensive process workflow for the application of AI-driven personalized cancer vaccines

April 08 2024 12:45 JST

NEC develops marketing strategy planning & effectiveness simulation technology using generative AI

March 25 2024 09:08 JST

NEC and NTT successfully conduct first-of-its-kind long-distance transmission experiment over 7,000km using 12-core optical fiber

March 22 2024 07:38 JST

NEC and Tokyo Medical and Dental University use AI to assist self-care for chronic lower back pain

March 21 2024 09:02 JST

NEC and Skyloom to Pioneer 100 Gbps Space Optical Communications, Transforming Global Internet Connectivity

March 20 2024 14:30 JST

NEC named to list of Top 100 Global Innovators by Clarivate for 13th consecutive year

March 07 2024 10:24 JST

More Press release >>

Latest Press Release

Mazda Production and Sales Results for March 2024 and for April 2023 through March 2024
Apr 25, 2024 18:21 JST

MHI Begins Operation of SOEC Test Module the Next-Generation High-Efficiency Hydrogen Production Technology at Takasago Hydrogen Park
Apr 25, 2024 17:45 JST

GAC Honda to Begin Sales of All-new e:NP2, the Second Model of e:N Series
Apr 25, 2024 16:50 JST

Toyota Exhibiting at Beijing Motor Show 2024
Apr 25, 2024 16:25 JST

Honda Reaches Basic Agreement with Asahi Kasei on Collaboration for Production of Battery Separators for Automotive Batteries in Canada
Apr 25, 2024 11:10 JST

UNIQLO Sponsors KAWS + Warhol Exhibition Tour, Starting in Pittsburgh
Apr 25, 2024 09:00 JST

Mitsubishi Power Begins Commercial Operation of Seventh M701JAC Gas Turbine in Thailand GTCC Project; Achieves 75,000 AOH To-Date
Apr 24, 2024 17:19 JST

MC and Denka Sign J/V Agreement in Fullerene Business
Apr 24, 2024 17:02 JST

Mitsubishi Motors Posts Record Sales in the Philippines in FY2023
Apr 24, 2024 13:56 JST

NEC Develops High-speed Generative AI Large Language Models (LLM) with World-class Performance
Apr 24, 2024 13:25 JST

Fujitsu SX Survey reveals key success factors for sustainability
Apr 23, 2024 10:25 JST

Fujitsu and METRON collaborate to drive ESG success: slashing energy costs, boosting productivity with new manufacturing industry solutions
Apr 22, 2024 16:09 JST

NEC Strengthens Commitment to Space Industry with Investment in Seraphim Space Venture Fund II
Apr 22, 2024 15:09 JST

Soft Space Launches the First and Only JCB Payment Gateway in Malaysia
Apr 22, 2024 15:00 JST

TOYOTA GAZOO Racing takes a one-two in Croatian thriller
Apr 22, 2024 10:47 JST

First-ever Mazda CX-80 Crossover SUV Unveiled in Europe
Apr 19, 2024 13:50 JST

Fujitsu develops technology to convert corporate digital identity credentials, enabling participation of non-European companies in European data spaces
Apr 19, 2024 10:17 JST

Mitsubishi Heavy Industries and NGK to Jointly Develop Hydrogen Purification System from Ammonia Cracking Gas
Apr 18, 2024 17:01 JST

Toyota Launches All-New Land Cruiser "250" Series in Japan
Apr 18, 2024 13:39 JST

Fujitsu and Oracle collaborate to deliver sovereign cloud and AI capabilities in Japan
Apr 18, 2024 11:14 JST

More Latest Release >>