Computing on device refers to the capability of running artificial intelligence (AI) models locally on a device rather than sending data to a remote server for processing.
It addresses the challenges of high latency in real-time applications and excessive power consumption when transmitting large amounts of data to remote servers for processing.
This technology allows AI models to run directly on the hardware of a device, such as smartphones or IoT devices, by optimizing the model's architecture and using specialized hardware accelerators. This minimizes latency and power consumption compared to cloud-based solutions where data must be transmitted over networks.
The manufacturing process involves optimizing existing hardware or designing new specialized hardware accelerators that can efficiently run AI models. This includes integrating these accelerators into devices like smartphones, tablets, and IoT gadgets.
Building computing on device solutions requires expertise in both software and hardware engineering. It involves model optimization techniques such as quantization, pruning, and knowledge distillation to reduce the computational requirements of AI models. Hardware design focuses on creating efficient silicon that can handle these optimized models without significant power draw.
Curated names only — none are invented. Use the link to find more.
Cost drivers only — no verified dollar figures are shown. Check live sources for prices.
Illustrative — search real, dated examples rather than trusting a generated story.
Live searches — we don't list papers we can't verify.
Live patent searches — filings are never listed from memory.
Verify against primary sources only.
Source: curated technology intelligence stream with tracked references.