Edge AI Inference
Running trained models on phones, cameras, vehicles, sensors, and embedded chips near data sources.
Core metadata
- ID: edge_ai_inference
- Era: Modern
- First known date: 2019 (exact)
- Region: Global edge-computing and machine-learning research community
- Review status: source_checked
- Maturity: established
Prerequisites
- Machine Learning (Early Algorithms) (machine_learning_early_algorithms)
- Microprocessors (CPU on a Chip) (microprocessors_cpu_on_a_chip)
Dependents
Fields
Field lanes
- Artificial Intelligence & Machine Learning: Deployment & MLOps
- Robotics & Autonomous Systems: Autonomy & AI
Node sources
- Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing (IEEE Transactions on Wireless Communications, 2020, primary_paper) • Supports: node, maturity
Prerequisite edge evidence
Edge/source evidence summary:
- Prerequisite edges: 2
- Average edge confidence: 70%
- Prerequisite sources: 2
- expert_inference: 2
| Prerequisite | Type | Confidence | Evidence level | Note | Sources |
|---|---|---|---|---|---|
| Machine Learning (Early Algorithms) (machine_learning_early_algorithms) | historical_predecessor | 75% | expert_inference | Machine Learning (Early Algorithms) is an earlier historical predecessor or foundation, not a one-to-one engineering dependency. |
|
| Microprocessors (CPU on a Chip) (microprocessors_cpu_on_a_chip) | commercial_or_scaling_dependency | 64% | expert_inference | Edge inference runs on embedded and mobile processors; microprocessors are deployment infrastructure rather than the machine-learning method itself. |
|
This page is generated from canonical era JSON and is indexable by URL.