Architecture-Aware Optimization of Layer Fusion for Latency-Optimal CNN Inference.
Minyong YoonJungwook ChoiPublished in: AICAS (2023)
Keyphrases
- optimal design
- multi layer
- joint optimization
- optimal selection
- optimization algorithm
- bayesian networks
- approximately optimal
- optimization problems
- constrained optimization
- inference engine
- cellular neural networks
- optimal solution
- hierarchical architecture
- finding optimal
- information fusion
- max min
- heterogeneous computing
- fusion method
- optimization process
- application layer
- global optimization
- closed form
- simultaneous optimization
- response time
- middle layer
- lower layers
- abstraction layer