Breaking News

Sony Unveils Sony FE 100mm F2.8 Macro GM OSS Creative Launches Aurvana Ace 3 GIGABYTE Announces Availability of 27” QHD 280Hz WOLED Gaming Monitor MO27Q28G with 4-Sided Borderless Design Crucial ® LPCAMM2 Powers AI-Ready Laptops With Breakthrough 8,533MT/s Speeds Logitech announces MX Master 4

logo

  • Share Us
    • Facebook
    • Twitter
  • Home
  • Home
  • News
  • Reviews
  • Essays
  • Forum
  • Legacy
  • About
    • Submit News

    • Contact Us
    • Privacy

    • Promotion
    • Advertise

    • RSS Feed
    • Site Map

Search form

Ricoh Develops Faster and  More Power Efficient AI Model Training

Ricoh Develops Faster and More Power Efficient AI Model Training

Enterprise & IT Dec 26,2018 0

Ricoh Company, Ltd. has developed a logic architecture that greatly speeds up Gradient Boosting Decision Tree (GBDT) model training and has significantly lower power consumption compared with traditional methods.

GBDT has been gaining increasing attention in the area of machine training, a form of AI training.

The developed logic architecture was implemented in a Field-Programmable Gate Array (FPGA: an integrated circuit where the designer can change the settings through programming) and the researchers compared training times and power efficiency with three general GBDT software libraries (XGBoost (extreme gradient boosting), LightGBM, CatBoost) using CPU and GPU. They saw that the training speed of the logic architecture on the FPGA was 26-259 times faster compared to the software libraries. In addition, power consumption during the training is low, and the power efficiency of the model training was 90-1,105 times lower compared with general GBDT software libraries using GPU and CPU. This low level of power consumption is especially suited to edge computing. The researchers also confirmed that the prediction accuracy of the trained model is equivalent to that learned from the software libraries.

"GBDT performs highly in the training of large volumes of structured data. We think high-speed training based on the developed logic architecture can contribute to online applications especially in areas such as real-time bidding in online advertisements and recommendations in e-commerce," Rucih said. In finance, the solution can be used in high-frequency trading of financial products by computer and in the security arena, the detection of cyber attacks, as well as in robotics. In addition, the developed logic architecture is suitable for edge devices and computing, which requires low power consumption.

The research group at the Ricoh Institute of Information and Communication Technology announced the results of their study on arXiv.org, a paper contribution website run by Cornell University, USA.

Tags: Artificial IntelligenceRicoh
Previous Post
Resarchers Develp Sound-based Touch Input Technology for Smart Tables and Mirrors
Next Post
Deep Learning Turns Mono Audio to 3D Sound

Related Posts

  • RICOH announces GR IV and GF-2 external flash

  • Ricoh 360 Theta A1 camera officially announced

  • RICOH announces development of GR IV

  • Ricoh establishes new industrial computer company in Japan

  • PENTAX 17 is simply a fixed-focal length compact film camera

  • Ricoh announces PENTAX WG-8 and PENTAX WG-1000 waterproof cameras

  • Ricoh announces GR III HDF and RICOH GR IIIx HDF

  • Ricoh announces PENTAX WG-90 waterproof digital compact camera

Latest News

Sony Unveils Sony FE 100mm F2.8 Macro GM OSS
Cameras

Sony Unveils Sony FE 100mm F2.8 Macro GM OSS

Creative Launches Aurvana Ace 3
Consumer Electronics

Creative Launches Aurvana Ace 3

GIGABYTE Announces Availability of 27” QHD 280Hz WOLED Gaming Monitor MO27Q28G with 4-Sided Borderless Design
Gaming

GIGABYTE Announces Availability of 27” QHD 280Hz WOLED Gaming Monitor MO27Q28G with 4-Sided Borderless Design

Crucial ® LPCAMM2 Powers AI-Ready Laptops With Breakthrough 8,533MT/s Speeds
Enterprise & IT

Crucial ® LPCAMM2 Powers AI-Ready Laptops With Breakthrough 8,533MT/s Speeds

Logitech announces MX Master 4
Enterprise & IT

Logitech announces MX Master 4

Popular Reviews

be quiet! Dark Mount Keyboard

be quiet! Dark Mount Keyboard

Terramaster F8-SSD

Terramaster F8-SSD

be quiet! Light Mount Keyboard

be quiet! Light Mount Keyboard

be quiet! Light Base 600 LX

be quiet! Light Base 600 LX

be quiet! Pure Base 501

be quiet! Pure Base 501

Soundpeats Pop Clip

Soundpeats Pop Clip

Akaso 360 Action camera

Akaso 360 Action camera

Dragon Touch Digital Calendar

Dragon Touch Digital Calendar

Main menu

  • Home
  • News
  • Reviews
  • Essays
  • Forum
  • Legacy
  • About
    • Submit News

    • Contact Us
    • Privacy

    • Promotion
    • Advertise

    • RSS Feed
    • Site Map
  • About
  • Privacy
  • Contact Us
  • Promotional Opportunities @ CdrInfo.com
  • Advertise on out site
  • Submit your News to our site
  • RSS Feed