Sökning: onr:"swepub:oai:DiVA.org:mdh-63960" >
Enhancing Fault Res...
Enhancing Fault Resilience of QNNs by Selective Neuron Splitting
-
- Ahmadilivani, M. H. (författare)
- Tallinn University of Technology, Tallinn, Estonia
-
- Taheri, M. (författare)
- Tallinn University of Technology, Tallinn, Estonia
-
- Raik, J. (författare)
- Tallinn University of Technology, Tallinn, Estonia
-
visa fler...
-
- Daneshtalab, Masoud (författare)
- Mälardalens universitet,Inbyggda system,Tallinn University of Technology, Tallinn, Estonia
-
- Jenihhin, M. (författare)
- Tallinn University of Technology, Tallinn, Estonia
-
visa färre...
-
(creator_code:org_t)
- Institute of Electrical and Electronics Engineers Inc. 2023
- 2023
- Engelska.
-
Ingår i: AICAS 2023 - IEEE International Conference on Artificial Intelligence Circuits and Systems, Proceeding. - : Institute of Electrical and Electronics Engineers Inc.. - 9798350332674
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- The superior performance of Deep Neural Networks (DNNs) has led to their application in various aspects of human life. Safety-critical applications are no exception and impose rigorous reliability requirements on DNNs. Quantized Neural Networks (QNNs) have emerged to tackle the complexity of DNN accelerators, however, they are more prone to reliability issues.In this paper, a recent analytical resilience assessment method is adapted for QNNs to identify critical neurons based on a Neuron Vulnerability Factor (NVF). Thereafter, a novel method for splitting the critical neurons is proposed that enables the design of a Lightweight Correction Unit (LCU) in the accelerator without redesigning its computational part.The method is validated by experiments on different QNNs and datasets. The results demonstrate that the proposed method for correcting the faults has a twice smaller overhead than a selective Triple Modular Redundancy (TMR) while achieving a similar level of fault resiliency.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Neurons
- Safety engineering
- Critical neurons
- Fault resilience
- Human lives
- Neural-networks
- Novel methods
- Performance
- Reliability requirements
- Safety critical applications
- Splittings
- Vulnerability factors
- Deep neural networks
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas