KFU. Card publication. An approach to reducing complexity of neuromorphic fault dictionary construction for analogue integrated circuits

KAZAN
FEDERAL UNIVERSITY

- RUS
- 中文
- ES

AN APPROACH TO REDUCING COMPLEXITY OF NEUROMORPHIC FAULT DICTIONARY CONSTRUCTION FOR ANALOGUE INTEGRATED CIRCUITS

Form of presentation

Articles in international journals and collections

Year of publication

2018

��

��

Authors, employees of KFU

Mosin Sergey Gennadevich, author

Bibliographic description in the original language

Mosin S., An approach to reducing complexity of neuromorphic fault dictionary construction for analogue integrated circuits//2018 28th International Conference Radioelektronika, RADIOELEKTRONIKA 2018. - 2018. - Vol., Is.. - P.1-6.

Annotation

This paper is mainly focused on the reducing a complexity of fault dictionary constructing for analog integrated circuits based on neural network. The benefits of fault dictionary based on neural network (NN) such as associative operating mode and small influence of the number of considered faults on the NN architecture are presented. The problems of constructing the neuromorphic fault dictionary in the aspect of big data are discussed. The approach to selection the essential characteristics of controlled parameters during testing and fault diagnostics as well as to reduction of the training set dimension is proposed. The principal component analysis and criterion based on the explained residual variance are applied for reduction the number of coefficients used for the neural network training. The decomposition of design flow corresponding to the proposed approach is presented. The experimental results demonstrates efficiency as the time and computational cost reduction.

Keywords

neuromorphic fault dictionary, principal component analysis, analog circuits, design-for-testability, testing and diagnostics

The name of the journal

2018 28th International Conference Radioelektronika, RADIOELEKTRONIKA 2018

URL

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85050003918&doi=10.1109%2fRADIOELEK.2018.8376404&partnerID=40&md5=9c3a5d68d412978f5b6ad12f1190dfbf

Please use this ID to quote from or refer to the card

https://repository.kpfu.ru/eng/?p_id=185201&p_lang=2

Full metadata record

Field DC	Value	Language
dc.contributor.author	Mosin Sergey Gennadevich	ru_RU
dc.date.accessioned	2018-01-01T00:00:00Z	ru_RU
dc.date.available	2018-01-01T00:00:00Z	ru_RU
dc.date.issued	2018	ru_RU
dc.identifier.citation	Mosin S., An approach to reducing complexity of neuromorphic fault dictionary construction for analogue integrated circuits//2018 28th International Conference Radioelektronika, RADIOELEKTRONIKA 2018. - 2018. - Vol., Is.. - P.1-6.	ru_RU
dc.identifier.uri	https://repository.kpfu.ru/eng/?p_id=185201&p_lang=2	ru_RU
dc.description.abstract	2018 28th International Conference Radioelektronika, RADIOELEKTRONIKA 2018	ru_RU
dc.description.abstract	This paper is mainly focused on the reducing a complexity of fault dictionary constructing for analog integrated circuits based on neural network. The benefits of fault dictionary based on neural network (NN) such as associative operating mode and small influence of the number of considered faults on the NN architecture are presented. The problems of constructing the neuromorphic fault dictionary in the aspect of big data are discussed. The approach to selection the essential characteristics of controlled parameters during testing and fault diagnostics as well as to reduction of the training set dimension is proposed. The principal component analysis and criterion based on the explained residual variance are applied for reduction the number of coefficients used for the neural network training. The decomposition of design flow corresponding to the proposed approach is presented. The experimental results demonstrates efficiency as the time and computational cost reduction.	ru_RU
dc.language.iso	ru	ru_RU
dc.subject	neuromorphic fault dictionary	ru_RU
dc.subject	principal component analysis	ru_RU
dc.subject	analog circuits	ru_RU
dc.subject	design-for-testability	ru_RU
dc.subject	testing and diagnostics	ru_RU
dc.title	An approach to reducing complexity of neuromorphic fault dictionary construction for analogue integrated circuits	ru_RU
dc.type	Articles in international journals and collections	ru_RU