Runtime configurable deep neural networks for energy-accuracy trade-off.
Hokchhay TannSoheil HashemiR. Iris BaharSherief RedaPublished in: CODES+ISSS (2016)
Keyphrases
- trade off
- neural network
- bias variance
- high accuracy
- computational cost
- error rate
- pattern recognition
- energy minimization
- energy consumption
- artificial intelligence
- classification accuracy
- prediction accuracy
- data sets
- cellular neural networks
- improved accuracy
- fuzzy logic
- genetic algorithm
- computational complexity
- self organizing maps
- fault diagnosis
- back propagation
- fuzzy systems
- energy efficiency
- accuracy rate