SCIENTIFIC PROGRESS
VOLUME 2
ǀ ISSUE 8
ǀ 2021
ISSN: 2181-1601
Uzbekistan
www.scientificprogress.uz
Page 287
NEYRON TARMOQLARINI O’RGANISHDA “TENSORFLOW”
IMKONIYATLARIDAN FOYDALANISH
Ahmadxon Avazxon o’g’li Qodirov
Muhammad al-Xorazmiy nomidagi Toshkent axborot texnologiyalari universiteti
Farg’ona
filiali
ANNOTATSIYA
Tensorflow - bu Google jamoasi tomonidan mashinani o'rganish va chuqur
o'rganish tushunchalarini eng oson tarzda amalga oshirish uchun ishlab chiqilgan dastur
kutubxonasi hisoblanadi. Kutubxona ko'plab matematik ifodalarni oson hisoblash uchun
optimallashtirish usullarini o’zida birlashtiradi.
Kalit so’zlar: Tensorflow, neyron tarmoq,
hisoblash grafi, Google, CPU, GPU,
taqsimlangan hisoblash.
USING TENSORFLOW FEATURES IN THE STUDY OF NEURAL
NETWORKS
ANNOTATION
TensorFlow
is a software library, designed by the Google team to implement
machine learning and deep learning concepts in the easiest manner.
It combines the
computational algebra of optimization techniques for easy calculation of many
mathematical expressions.
Keywords: Tensorflow, Neural Network, Calculation graph, Google, CPU, GPU,
distributed calculation.
KIRISH
Tensorflow - “Google Brain” jamoasi tomonidan yaratilgan raqamli hisoblash va
keng ko'lamli mashinani o'rganish uchun ochiq kodli kutubxona. Tensorflow to'plamlari
birgalikda mashinalarni o'rganish va chuqur o'rganish modellari
va algoritmlari bilan
birga, va ularni umumiy metafora bilan foydali qiladi. Ushbu dasturlarni yuqori
samarali C ++ tillarida amalga oshirishda ramkalar
yordamida ushbu dasturlarni
bajarishda ramka bilan arizalarni yaratish uchun qulay API interfeysini taqdim etish
uchun Pythondan foydalanadi.
