Foydalanilgan internet saytlari.
https://en.wikipedia.org/wiki/Artificial_neural_network
https://www.geeksforgeeks.org/implementing-models-of-artificial-neural-network/
https://towardsdatascience.com/applied-deep-learning-part-1-artificial-neural-networks-d7834f67a4f6#106c
https://www.ibm.com/cloud/learn/neural-networks
https://medium.com/analytics-vidhya/artificial-neural-networks-an-intuitive-approach-part-1-890efac210f0
https://www.mygreatlearning.com/blog/types-of-neural-networks/
https://towardsdatascience.com/a-journey-through-neural-networks-part-1-artificial-neural-network-and-perceptron-e970614b9cc7
https://viso.ai/deep-learning/artificial-neural-network/
https://medium.com/datasciencearth/basic-structure-of-artificial-neural-networks-9aef29df9d
https://www.geeksforgeeks.org/introduction-to-artificial-neutral-networks/
https://www.javatpoint.com/artificial-neural-network
https://brilliant.org/wiki/artificial-neural-network/
https://natureofcode.com/book/chapter-10-neural-networks/
Ilova
2 qatlamli neyron tarmoq:
import numpy as np
# sigmoid function
def nonlin(x,deriv=False):
if(deriv==True):
return x*(1-x)
return 1/(1+np.exp(-x))
# input dataset
X = np.array([ [0,0,1],
[0,1,1],
[1,0,1],
[1,1,1] ])
# output dataset
y = np.array([[0,0,1,1]]).T
# seed random numbers to make calculation
# deterministic (just a good practice)
np.random.seed(1)
# initialize weights randomly with mean 0
syn0 = 2*np.random.random((3,1)) - 1
for iter in xrange(10000):
# forward propagation
l0 = X
l1 = nonlin(np.dot(l0,syn0))
# how much did we miss?
l1_error = y - l1
# multiply how much we missed by the
# slope of the sigmoid at the values in l1
l1_delta = l1_error * nonlin(l1,True)
# update weights
syn0 += np.dot(l0.T,l1_delta)
print "Output After Training:"
print l1
Treningdan keyingi natijalar:
[[ 0.00966449]
[0,00786506]
[0.99358898]
[0.99211957]]
|