Казанский (Приволжский) федеральный университет, КФУ
КАЗАНСКИЙ
ФЕДЕРАЛЬНЫЙ УНИВЕРСИТЕТ
 
ENTROPY-BASED METHOD OF REDUCING THE TRAINING SET DIMENSION AT CONSTRUCTING A NEUROMORPHIC FAULT DICTIONARY FOR ANALOG AND MIXED-SIGNAL ICS
Форма представленияСтатьи в зарубежных журналах и сборниках
Год публикации2018
Языканглийский
  • Мосин Сергей Геннадьевич, автор
  • Библиографическое описание на языке оригинала Mosin S., Entropy-based method of reducing the training set dimension at constructing a neuromorphic fault dictionary for analog and mixed-signal ICs//2018 7th Mediterranean Conference on Embedded Computing, MECO 2018 - Including ECYPS 2018, Proceedings. - 2018. - Vol., Is.. - P.1-4.
    Аннотация The effect of faults on the circuit operating is usually evaluated by simulation, using the appropriate models of catastrophic and parametric faults. Functional and structural complexity, consideration of the tolerances on the components parameters, the infinity of the set of parametric faults, etc., leads to the accumulation of large amounts of data describing the behavior of the fault-free and faulty states of the circuit. Machine learning methods are actively used to construct neuromorphic fault dictionaries (NFD), which provide fault diagnostics of analog and mixed-signal integrated circuits. Many problems of training a neural network with a large amount of data can be solved by reducing the size of training sets and using only significant characteristics in them. The paper proposes a method based on calculating entropy to select the essential characteristics for a training set. An algorithm for reducing the dimension of a training set using entropy is presented.
    Ключевые слова fault diagnostics, analog and mixed-signal integrated circuits, neuromorphic fault dictionary, entropy, training set reduction, machine learning
    Название журнала 2018 7th Mediterranean Conference on Embedded Computing, MECO 2018 - Including ECYPS 2018, Proceedings
    URL https://www.scopus.com/inward/record.uri?eid=2-s2.0-85050683658&doi=10.1109%2fMECO.2018.8406093&partnerID=40&md5=6e51be67b1d1e7b168eaa4e09c4b2b2a
    Пожалуйста, используйте этот идентификатор, чтобы цитировать или ссылаться на эту карточку https://repository.kpfu.ru/?p_id=185202

    Полная запись метаданных