Sheela
Sheela
Home
Add
Questions
Thinkers
Claims
People
Concepts
Jargon
Sources
Health
Predictions
Collections
Domain Landscape
Contribute
Review
Dedup
Topic requests
Settings
Help

← Jargon

Jargonmachine learning· 3 claims· 1 episode

Edge inference

Running machine learning inference on the device itself rather than sending raw data to the cloud.

As defined in Ray Ozzie - The Future of Intelligent Machines - [Invest Like the Best, EP.391]


Where it comes up · 1
  • Ray Ozzie - The Future of Intelligent Machines - [Invest Like the Best, EP.391]3 claims

Most important claims · 3 of 3Search all claims for “Edge inference” →
  • A startup in Ukraine uses cheap Android phones that listen for the acoustic signatures of specific drones and missiles, uses machine learning to classify them, and correlates trajectories to project likely impact points, which are then shared through Telegram channels combining bots and people.Ray Ozzie - The Future of Intelligent Machines - [Invest Like the Best, EP.391]
  • All physical devices are going to become intelligent machines, with intelligence split across the device and the cloud, and the split varies with the device's cost parameters and use case.Ray Ozzie - The Future of Intelligent Machines - [Invest Like the Best, EP.391]
  • Small and medium manufacturers mainly want a data pump that moves data from devices to the cloud, and increasingly want edge inference for anomaly detection, rather than building their own telemetry stack.Ray Ozzie - The Future of Intelligent Machines - [Invest Like the Best, EP.391]