Edge AI
Edge AI
Edge AI definition
Edge AI refers to the deployment of AI algorithms directly on endpoint devices, as opposed to running the computations in a centralized data center or in the cloud. These endpoint devices can include anything from smartphones and tablets to edge servers and gateways located closer to the source of data.
See also: augmented intelligence, artificial intelligence
Edge AI benefits
- Low latency. It processes data directly on the device, enabling it to provide real-time insights without sending data to a central server for processing.
- Privacy and security. Data doesn’t need to be sent to a central server, reducing the risk of exposing data.
- Bandwidth efficiency. Transmitting everything to a central server and back can take a toll on the network. Edge AI conserves bandwidth because only relevant insights or more compact processed data is sent.
- Operational continuity. It allows applications to work even if network connection is lost. This is especially important for autonomous vehicles and medical devices.
- Energy efficiency. Edge devices often use less energy.
Edge AI use cases
- Autonomous vehicles. Edge AI allows self-driving cars to process sensor data and make driving decisions instantly.
- Smart cameras. Cameras in public places or at businesses might use Edge AI to analyze footage in real-time, identifying suspicious behaviors, counting people, or recognizing license plates without sending video streams to a central server.
- Healthcare. Wearable devices can use Edge AI to detect critical situations, triggering an alarm immediately.
- Agriculture. Smart farming equipment can use Edge AI to analyze soil conditions, optimize irrigation, or detect pests/disease.