Sun’iy intellekt va neyron tarmoqlari

Tasvirlarni sinflashtirishning klassik yondashuviga mos javobni tanlang.

O’quv to’plamini yig’ish • Mashinali o’qitish asosida sinflash bloklarini o’qitish • Sinf natijasini sinflash bloki yordamida bashorat qilish

15. 
    Neyron tarmoq turlari mos javobni aniqlang.
    

Perceptron
• Feed Forward (FF)
• Radial Basis Network (RBN)
• Deep Feed Forward (DFF)
• Convolution Neural Network (CNN)
• Recurrent Neural Network (RNN)
• Long/Short Term Memory (LSTM)
• Gated Recurrent Unit (GRU)
• Auto Encoder (AE)
• Variational AE (VAE)
• Denoising AE (DAE)
• Sparse AE (SAE)

15. 
    Convolutional neural networks (CNN) – bu…
    

bu ko'p qatlamli neyron tarmoq hamda noyob arxitekturaga ega bo’lib, har bir qatlamda ma'lumotlarning tobora murakkab xususiyatlarini chiqish uchun aniqlashga mo'ljallangan. CNN lar tanib olish masalalarini yechishda, sinflashtirish masalalarida keng foydalaniladi.

15. 
    Convolutional neural networks (CNN)da kirish qatlami nima vazifani bajaradi?
    

Neyron tarmoq kirish qatlami tasvirni o’qib oladi

15. 
    Convolutional neural networks (CNN)da “Convolution” tushunchasiga mos izohni tanlang.
    

kiruvchi tasvirni filtr asosida sirpanuvchi oyna usulida (convolution) hisoblash

15. 
    Convolutional neural networks (CNN)da “Pooling” tushunchasiga mos izohni tanlang.
    

convolution dan keyin amalga oshiriladigan (max, min, average) hisoblash jarayoni


36. Convolutional neural networks (CNN)da “ReLU” tushunchasiga mos izohni tanlang.
aktivatsiya funksiyasi

37. 
    Convolutional neural networks (CNN)da “Fully connected” tushunchasiga mos izohni tanlang.
    

bu neyron tarmoq chiqishi uchun, convolution asosida hosil bo’lgan qiymatlarni to’liq bog’langan neyronlar ko’rinishiga o’tkazish

37.