A Low-Cost Training Method of ReRAM Inference Accelerator Chips for Binarized Neural Networks to Recover Accuracy Degradation due to Statistical Variabilities.
Zian ChenTakashi OhsawaPublished in: IEICE Trans. Electron. (2022)
Keyphrases
- high accuracy
- low cost
- neural network
- computational cost
- high precision
- training process
- error rate
- statistical information
- detection method
- highly accurate
- computational efficiency
- inference process
- edge detection
- classification accuracy
- probabilistic model
- training algorithm
- significant improvement
- accuracy rate
- feed forward neural networks
- parameter estimation
- correlation coefficient
- neural nets
- bayesian inference
- statistical inference
- bayesian networks