This paper proposes a novel method that performs model quantization while remarkably improving the fault-tolerance of the model. It can be incorporated with other hardware approaches such as Error Correcting Code to further improve fault-tolerance.
Abstract—Deep Neural Networks (DNNs) are deployed in many real-time and safety-critical applications such as autonomous vehicles and medical diagnosis.
A statistical quantization model is used to analyze of the effects of quantization in digital implementation of high-order function neural network.
RQ-DNN: Reliable Quantization for Fault-tolerant Deep Neural Networks. DAC ... Bipolar vector classifier for fault-tolerant deep neural networks. DAC ...
The proposed method reduces possible error patterns that negatively impact classification accuracy by modifying weight distributions and applying a novel ...
Rq-dnn: Reliable quantization for fault-tolerant deep neural networks. I Choi, JY Hong, JH Jeon, JS Yang. 2023 60th ACM/IEEE Design Automation Conference (DAC) ...
Hong, J. Jeon, and J.-S. Yang, “RQ-DNN: Reliable Quantization for Fault-tolerant Deep Neural Network,” ACM/IEEE Design Automation Conference Late Breaking ...
People also ask
What is DNN Quantization?
Is neural network fault tolerant?
This article proposes CRAFT, i.e., criticality-aware fault-tolerance enhancement techniques to enhance the reliability of NVM-based DNNs in the presence of ...
Apr 25, 2024 · RQ-DNN: Reliable Quantization for Fault-tolerant Deep Neural Networks. DAC 2023: 1-2. [c1]. view. electronic edition via DOI · unpaywalled ...
Late Breaking Results: RQ-DNN: Reliable Quantization for Fault-tolerant Deep Neural Network. add to My Agenda remove from My Agenda. AI. Autonomous Systems.