DaiMoN introduces a decentralized ledger-based network for collaborative ML model improvement with label-hidden proof-of-improvement enabled by a novel learnable Distance Embedding for Labels (DEL) function.
Learning internal representations by error propagation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2019 2verdicts
UNVERDICTED 2representative citing papers
Sensitivity-ranked remapping of kernels in resistive crossbars limits line-resistance accuracy drop from 5.6% to 2.1-2.9% on VGG16/CIFAR10 without retraining.
citing papers explorer
-
DaiMoN: A Decentralized Artificial Intelligence Model Network
DaiMoN introduces a decentralized ledger-based network for collaborative ML model improvement with label-hidden proof-of-improvement enabled by a novel learnable Distance Embedding for Labels (DEL) function.
-
X-CHANGR: Changing Memristive Crossbar Mapping for Mitigating Line-Resistance Induced Accuracy Degradation in Deep Neural Networks
Sensitivity-ranked remapping of kernels in resistive crossbars limits line-resistance accuracy drop from 5.6% to 2.1-2.9% on VGG16/CIFAR10 without retraining.