iOty

iOty

iOty is a project that implements DNN on the edge for faster inference compared to a cloud-only approach.

Artificial Intelligence

  • 1 Collaborators

  • 239 Followers

    Follow

Description

Nowadays, the training phase of AI -- which is highly compute-intensive -- is being increasingly sped up by cloud computing. However, communicating with the cloud introduces latency during AI inference phase, which leads to poor performance for applications requiring 'hard' real-time responses from an on-premise location. We define "hard real-time" as a microsecond timescale, end-to-end, for a single batch of data communication and data processing. We propose iOty, a distributed architecture for accelerated DNNs on the edge. The main objective of the iOty project is to design and build an AI software and hardware system with real-time inference capabilities for edge applications that exhibit high-speed, massive dataset characteristics wherein communicating with the cloud directly would be impractical or too expensive.

Github: https://github.com/davenso/edgenn

15934164 1204653962936463 1111344975 o

David O. added photos to project iOty

Medium c7153c70 d6a9 43d0 aa76 2a418294a2b0

iOty

Nowadays, the training phase of AI -- which is highly compute-intensive -- is being increasingly sped up by cloud computing. However, communicating with the cloud introduces latency during AI inference phase, which leads to poor performance for applications requiring 'hard' real-time responses from an on-premise location. We define "hard real-time" as a microsecond timescale, end-to-end, for a single batch of data communication and data processing. We propose iOty, a distributed architecture for accelerated DNNs on the edge. The main objective of the iOty project is to design and build an AI software and hardware system with real-time inference capabilities for edge applications that exhibit high-speed, massive dataset characteristics wherein communicating with the cloud directly would be impractical or too expensive.

Github: https://github.com/davenso/edgenn

15934164 1204653962936463 1111344975 o

David O. added photos to project iOty

Medium c7153c70 d6a9 43d0 aa76 2a418294a2b0

iOty

Nowadays, the training phase of AI -- which is highly compute-intensive -- is being increasingly sped up by cloud computing. However, communicating with the cloud introduces latency during AI inference phase, which leads to poor performance for applications requiring 'hard' real-time responses from an on-premise location. We define "hard real-time" as a microsecond timescale, end-to-end, for a single batch of data communication and data processing. We propose iOty, a distributed architecture for accelerated DNNs on the edge. The main objective of the iOty project is to design and build an AI software and hardware system with real-time inference capabilities for edge applications that exhibit high-speed, massive dataset characteristics wherein communicating with the cloud directly would be impractical or too expensive.

Github: https://github.com/davenso/edgenn

Medium 15934164 1204653962936463 1111344975 o

David O. created project iOty

Medium c7153c70 d6a9 43d0 aa76 2a418294a2b0

iOty

Nowadays, the training phase of AI -- which is highly compute-intensive -- is being increasingly sped up by cloud computing. However, communicating with the cloud introduces latency during AI inference phase, which leads to poor performance for applications requiring 'hard' real-time responses from an on-premise location. We define "hard real-time" as a microsecond timescale, end-to-end, for a single batch of data communication and data processing. We propose iOty, a distributed architecture for accelerated DNNs on the edge. The main objective of the iOty project is to design and build an AI software and hardware system with real-time inference capabilities for edge applications that exhibit high-speed, massive dataset characteristics wherein communicating with the cloud directly would be impractical or too expensive.

Github: https://github.com/davenso/edgenn

Bigger 16174471 1640120109348229 5329353573964776870 n
Student Ambassador
  • Projects 3
  • Followers 131

Vidhi Jain

Mitacs Globalink Intern at Simon Fraser, Canada | Intern at Forschungszentrum Informatik (FZI), Germany | Citi Women Leader 2017 | GE Foundation Leader Scholar 2016 | Project Coordinator ACM Student Chapter | Founder and Vice Chair ACM-W Student Chapter

41, Paschim Marg, BITS, Pilani, Rajasthan 333031, India

Bigger 0 xfzyqlmonjtqoehuacdskbz2bqd uq8cuah4t7xofz2qoeic4vhutejunjg8oo7rs9hxkezdbpsqhbt vuk1ie4erps6hb zwukynlxo56pfhh awhnxrvszyc
  • Projects 0
  • Followers 2

AAYUSH VARSHNEY

Lucknow Metropolitan Area, Uttar Pradesh

Default user avatar 57012e2942
  • Projects 0
  • Followers 0

Jong Hee Kim

Kuala Lumpur, Federal Territory of Kuala Lumpur, Malaysia

Default user avatar 57012e2942
  • Projects 0
  • Followers 2

Praveen C Naik

6, Vijayashri Layout, Syndicate Bank Colony, Omkar Nagar, Arekere, Bengaluru, Karnataka 560076, India

Default user avatar 57012e2942
  • Projects 0
  • Followers 3

OLIVIA NAKAYIMA

Olivia is a young lady so passionate in networking and AI. She is currently undertaking a networking opportunity.

Kampala, Uganda

Bigger 14721653 1225197637521491 2418553984361348570 n
Student Ambassador
  • Projects 2
  • Followers 10

alfred ongere

Final year student, Telecommunications and Information engineering, Intel Student Partner for Multimedia University since 2016 to present.

Nairobi, Kenya

See More