ALWANN: Automatic Layer-Wise Approximation of Deep Neural Network Accelerators without Retraining.
Vojtech MrazekZdenek VasícekLukás SekaninaMuhammad Abdullah HanifMuhammad ShafiquePublished in: ICCAD (2019)
Keyphrases
- neural network
- multi layer
- artificial neural networks
- multiple layers
- single layer
- real time
- back propagation
- fully automatic
- pattern recognition
- pairwise
- semi automatic
- prediction model
- computing systems
- approximation methods
- computing platform
- fuzzy neural network
- fermentation process
- neural nets
- approximation algorithms
- feed forward
- closed form
- self organizing maps
- special case
- genetic algorithm