Pith. sign in

Exploring the impact of random tele- graph noise-induced accuracy loss on resistive RAM- based deep neural network

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

other 1

citation-polarity summary

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

roles

other 1

polarities

unclear 1

representative citing papers

On Hardening DNNs against Noisy Computations

cs.LG · 2025-01-24 · conditional · novelty 4.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • On Hardening DNNs against Noisy Computations cs.LG · 2025-01-24 · conditional · none · ref 6

    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.