TelecomTV TelecomTV
  • News
  • Videos
  • Channels
  • Events
  • Directory
  • Smart Studio
  • Surveys
  • Debates
  • Perspectives
  • DSP Leaders World Forum
  • DSP Leaders
  • Great Telco Debate
    • |
    • Follow
    • |
    • Subscribe
  • |
  • More
  • Webcasts
  • Surveys
  • Debates
  • Perspectives
  • Great Telco Debate
  • |
  • Follow TelecomTV
  • |
    • Subscribe
    • |
  • About
  • Privacy
  • Help
  • Contact
  • Follow TelecomTV
  • About
  • Privacy
  • Help
  • Contact
  • Sign In Register Subscribe
    • Subscribe
    • Sign In
    • Register
  • Search

Tracker

TelecomTV TRACKER

Sourced by TelecomTV's TRACKER platform
from NEC News room

Tracker

NEC develops deep learning technology to improve recognition accuracy

Via NEC News room

Dec 12, 2017

Tokyo, December 12, 2017 - NEC Corporation (NEC; 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."

Larger view

Automatic configuration of regularization at each layer of an artificial neural network

Related Topics
  • Announcement,
  • Asia-Pacific,
  • NEC,
  • News,
  • Tracker

More Like This

Open RAN

Keysight selected by Radisys to create open radio access network test environment

Jan 20, 2021

Edge

Telefónica opens up its 5G network and edge computing to startups to develop new services

Jan 20, 2021

5G

EE Enters 2021 as UK’s Leading Network

Jan 20, 2021

AI, Analytics & Automation

Telcos turn to AI and operations automation in 5G networks: ABI Research

Jan 20, 2021

5G

Telstra, Ericsson and Qualcomm achieve record of 5Gbps 5G download speed on a commercial network

Jan 19, 2021

This content extract was originally sourced from an external website (NEC News room) and is the copyright of the external website owner. TelecomTV is not responsible for the content of external websites. Legal Notices

Email Newsletters

Stay up to date with the latest industry developments: sign up to receive TelecomTV's top news and videos plus exclusive subscriber-only content direct to your inbox – including our daily news briefing and weekly wrap.

Subscribe

Top Picks

Highlights of our content from across TelecomTV today

1:4:29

Great Telco Debate: Live Debate – Day 2 (On-demand)

1:18:20

Great Telco Debate: Live Debate – Day 3 (On-demand)

43:08

Developing an ecosystem for vRAN

2:23

The TelecomTV Snapshot: The Great Telco Debate 2020 - CSP Highlights

  • TelecomTV
  • Decisive Media

TelecomTV is produced by the team at Decisive Media

Menu
  • News
  • Videos
  • Channels
  • Directory
  • Smart Studio
 
  • Surveys
  • Debates
  • Perspectives
  • Events
  • About Us
Our Brands
  • TelecomTV Tracker
  • TelecomTV Perspectives
  • DSP Leaders
  • DSP Leaders World Forum
  • The Great Telco Debate
Get In Touch
[email protected]
+44 (0) 207 448 1070

Request a Media Pack

Follow
  • © Decisive Media Limited 2021. All rights reserved. All brands and products are the trademarks of their respective holder(s).
  • Privacy
  • Terms
  • Legal Notices