On CIFAR-10, quantization-aware training with large constant scaling factors improves noise robustness, but noisy training (injecting matching Gaussian noise during training) gives far larger robustness gains, and quantization adds little on top of it.
Precise neural network computation with imprecise analog devices
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
The operations used for neural network computation map favorably onto simple analog circuits, which outshine their digital counterparts in terms of compactness and efficiency. Nevertheless, such implementations have been largely supplanted by digital designs, partly because of device mismatch effects due to material and fabrication imperfections. We propose a framework that exploits the power of deep learning to compensate for this mismatch by incorporating the measured device variations as constraints in the neural network training process. This eliminates the need for mismatch minimization strategies and allows circuit complexity and power-consumption to be reduced to a minimum. Our results, based on large-scale simulations as well as a prototype VLSI chip implementation indicate a processing efficiency comparable to current state-of-art digital implementations. This method is suitable for future technology based on nanodevices with large variability, such as memristive arrays.
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
On Hardening DNNs against Noisy Computations
On CIFAR-10, quantization-aware training with large constant scaling factors improves noise robustness, but noisy training (injecting matching Gaussian noise during training) gives far larger robustness gains, and quantization adds little on top of it.