☰
Notes
🔍
×
Statistics
Supervised Learning
Unsupervised Learning
Deep Learning
Reinforcement Learning
Edge AI
Foundations & Concepts
▼
Edge Hardware
Mobile Processors
Embedded Accelerators
Microcontrollers
▼
Model Optimization for Edge
Quantization for Edge
Structural Compression
Knowledge Distillation for Edge
Hardware-Aware NAS
▼
Compilation & Runtimes
Runtimes & Frameworks
Compilation & Graph Optimization
▼
Deployment & Operations
Edge Inference Patterns
On-Device Training & Personalization
Fleet Operations
▼
Device & Workload Classes
TinyML
Mobile ML
IoT & Sensor ML
On-Device LLMs
Privacy & Security at Edge
Performance & Benchmarking
Applications
AI ML
>
Edge AI
>
Deployment & Operati…
>
Edge Inference Patte…
Overview
◀
Map
Tree
Terms
Read
▶
Resources
Quiz
Play
🔍
×
By term
By resource
3
links
×
Filters
▾
Site
All
3
arxiv.org
3
Deployment & Operations
›
Edge Inference Patterns
2 terms
Early Exit
1 link
A
BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks
Pap…
Split Computing
2 links
A
Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge
Pap…
A
Edgent: On-Demand DNN Co-Inference with Device–Edge Synergy
Pap…
A
BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks
Pap…
1 term
Early Exit
A
Edgent: On-Demand DNN Co-Inference with Device–Edge Synergy
Pap…
1 term
Split Computing
A
Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge
Pap…
1 term
Split Computing
No terms or links match your search.
Term
Open full page
↗
Loading...