FakeInf: Selective Deep Neural Network Inference for Latency and Energy-Aware Model Serving Pipelines

Keyphrases

• Latency-aware 100%
• Deep Neural Network Inference 100%
• Edge Computing Nodes 50%
• Model Update 50%
• Smart Traffic Control System 50%
• Resource-constrained 50%
• Traffic Energy 50%
• Full Model 50%
• Real-time Inference 50%
• Decision Module 50%
• Traffic Latency 50%

Computer Science

• Statistical Estimation 50%