Accuracy, Training Time and Hardware Efficiency Trade-Offs for Quantized Neural Networks on FPGAs.
Pascal BacchusRobert J. StewartEkaterina KomendantskayaPublished in: ARC (2020)
Keyphrases
- neural network
- trade off
- training process
- training algorithm
- field programmable gate array
- high accuracy
- real time
- hardware software
- computational cost
- low cost
- computational efficiency
- hardware implementation
- hardware and software
- training set
- test set
- hardware design
- pattern recognition
- feed forward neural networks
- computational complexity
- prediction accuracy
- training speed
- backpropagation algorithm
- feedforward neural networks
- classification accuracy
- fuzzy logic
- embedded systems
- neural network model
- training samples
- error rate
- genetic algorithm
- neural network training
- error back propagation