O'zgaruvchan
|
Ta'rif
|
X
|
Har bir qator oʻquv namunasi boʻlgan maʼlumotlar toʻplami matritsasi kiritiladi
|
Y
|
Har bir satr oʻquv namunasi boʻlgan chiqish maʼlumotlar majmuasi matritsasi
|
l0
|
Tarmoqning birinchi qatlami, kirish ma'lumotlari bilan belgilanadi
|
l1
|
Tarmoqning ikkinchi qatlami, aks holda yashirin qatlam deb ataladi
|
syn0
|
Og'irliklarning birinchi qatlami, Synapse 0, l0 ni l1 bilan bog'laydi.
|
*
|
Elementlar bo'yicha ko'paytirish, shuning uchun teng o'lchamdagi ikkita vektor bir xil o'lchamdagi yakuniy vektorni yaratish uchun mos qiymatlarni 1 dan 1 gacha ko'paytiradi.
|
-
|
Elementlar bo'yicha ayirish, shuning uchun teng o'lchamdagi ikkita vektor bir xil o'lchamdagi yakuniy vektorni yaratish uchun 1 dan 1 gacha mos qiymatlarni ayiradi.
|
x.nuqta(y)
|
Agar x va y vektorlar bo'lsa, bu nuqta mahsulotidir. Agar ikkalasi ham matritsa bo'lsa, bu matritsa-matritsani ko'paytirish. Agar bitta matritsa bo'lsa, u vektor matritsani ko'paytirishdir.
|
3 qatlamli neyron tarmoq:
import numpy as np
def nonlin(x,deriv=False):
if(deriv==True):
return x*(1-x)
return 1/(1+np.exp(-x))
X = np.array([[0,0,1],
[0,1,1],
[1,0,1],
[1,1,1]])
y = np.array([[0],
[1],
[1],
[0]])
np.random.seed(1)
# randomly initialize our weights with mean 0
syn0 = 2*np.random.random((3,4)) - 1
syn1 = 2*np.random.random((4,1)) - 1
for j in xrange(60000):
# Feed forward through layers 0, 1, and 2
l0 = X
l1 = nonlin(np.dot(l0,syn0))
l2 = nonlin(np.dot(l1,syn1))
# how much did we miss the target value?
l2_error = y - l2
if (j% 10000) == 0:
print "Error:" + str(np.mean(np.abs(l2_error)))
# in what direction is the target value?
# were we really sure? if so, don't change too much.
l2_delta = l2_error*nonlin(l2,deriv=True)
# how much did each l1 value contribute to the l2 error (according to the weights)?
l1_error = l2_delta.dot(syn1.T)
# in what direction is the target l1?
# were we really sure? if so, don't change too much.
l1_delta = l1_error * nonlin(l1,deriv=True)
syn1 += l1.T.dot(l2_delta)
syn0 += l0.T.dot(l1_delta)
Xato: 0.496410031903
Xato: 0.00858452565325
Xato: 0.00578945986251
Xato: 0.00462917677677
Xato: 0.00395876528027
Xato: 0.00351012256786
|