Carrier Cloud for Deep Learning to Enable Highly Efficient Inference Processing--R&amp;D Technologies as a Source of Competitive Power in Company Activities

Hamuro, Daisuke; Iida, Koji; Usami, Kiyotada; Yura, S.; Matsuo, Yosuke; Eda, Takeharu; Sakamoto, Akira; Toyama, Masashi; Mikami, K.; Inoue, Noriaki; Nakayama, Ryuji; Enomoto, Shohei; Sasaki, Taku; Xu, Shengyuan; Hirokawa, Yutaka; Inaya, Katsuo

doi:10.53829/ntr202001fa2

Cited by 2 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial intelligence (AI) technologies such as deep learning are being applied to many commercial services worldwide and steadily progressing towards disruptive advances for real business [1]. NTT has initiated the concept of the Innovative Optical and Wireless Network (IOWN) and is developing more advanced AI-based cognitive, autonomous, and predictive systems that can recognize what humans cannot, handle much larger-scale problems than humans can do, and make decisions much quicker than humans.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Event-driven Inference Approach to Support AI Applications in IOWN Era

Eda

Kurebayashi

et al. 2021

NTT Technical Review

Self Cite

View full text Add to dashboard Cite

Artificial intelligence (AI) in the Innovative Optical and Wireless Network (IOWN) era is expected to not only acquire capabilities beyond humans but also be energy-efficient, therefore contribute to the sustainability of future societies. This article describes an event-driven inference approach as a promising approach to balance AI capabilities and efficiency. This approach efficiently inspects continuous input stream data and generates events that trigger subsequent deeper inference tasks over geographically distributed computing resources only when they are truly necessary. This approach will significantly decrease energy consumption and computational and networking costs in AI inference.

show abstract

Section: Introductionmentioning

confidence: 99%

An Efficient Event-driven Inference Approach to Support AI Applications in IOWN Era

Eda

Kurebayashi

et al. 2021

NTT Technical Review

Self Cite

View full text Add to dashboard Cite

show abstract

Phygital-data-centric Computing

Kawashima

2020

NTT Technical Review

View full text Add to dashboard Cite

The artificial intelligence (AI)/Internet of Things initiatives being undertaken in many countries will lead to a new computing paradigm called phygital-data-centric computing, which will create data servers near the physical world and their clients on the cloud. NTT Software Innovation Center is developing technologies necessary for value-generating, cost-effective, and operable phygital-data-centric computing. In particular, it is conducting research and development in three focus areas, 1) AI computing infrastructure, 2) data hub/pipelines, and 3) advanced analytics.

show abstract

Carrier Cloud for Deep Learning to Enable Highly Efficient Inference Processing--R&D Technologies as a Source of Competitive Power in Company Activities

Abstract: This article introduces efficient inference technology as an important element in applying deep learning to business and an inference cloud service that is combined with NTT Group assets such as telephone exchange buildings and base stations.

Cited by 2 publications

References 1 publication

An Efficient Event-driven Inference Approach to Support AI Applications in IOWN Era

An Efficient Event-driven Inference Approach to Support AI Applications in IOWN Era

Phygital-data-centric Computing

Contact Info

Product

Resources

About