1-amaliy topshiriq

1-amaliy topshiriq.
1-dastur. Bir va ko’p qatlamli sun’iy neyron to’rlari bo’yicha dastur tuzish (Python dasturlash tilida).
Aytaylik, bizning ikkita kirish neyronimiz sigmasimon faollashtirish funktsiyasidan foydalanadi va quyidagi parametrlarga ega:
w=[0,1], b=8
w=[0, 1] vektor shaklida faqat w₁=0, w₂=1. Endi neyronga kirish ma'lumotlarimizni beramiz: x=[4, 5]. Formulani siqilgan shaklda yozish uchun vektorlarning nuqta mahsulotidan foydalanamiz:
(w x)+b=((w₁*x₁)+(w₂*x₂))+b=0*4+1*5=5
y=f((w x)+b)=f(5)= 0,999

Bizning neyronimiz x=[2, 3] kirishlar uchun 0,999 chiqadi.

Dastur qism:
import numpy as np

weights = np.array([0, 1]) # w1 = 0, w2 = 1

bias = 8 # b = 8
n = Neuron(weights, bias)

x = np.array([4, 5]) # x1 = 4, x2 = 5

print(n.feedforward(x))
Natija:



2-dastur. Perseptron. Perseptron modeli bo’yicha dastur tuzish ( Python dasturlash tilida ).
Tensorflow bilan foydalanish misoli.
Biz bir xil MNIST ma'lumotlar to'plamidagi raqamlarni tasniflaymiz.
Dastur qismi:
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x, W) + b)
y_ = tf.placeholder(tf.float32, [None, 10])
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print("Accuracy: %s" % sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
Natija:






3-dastur. Sun’iy neyron to’rini o’qituvchili va o’qituvchisiz o’rgatish bo’yicha dastur tuzish (Python dasturlash tilida).
Main.py fayliga o'qitish uchun ma'lumotlar va to'g'ri javoblar bilan massiv qo'shamiz:

Dastur qismi:
import numpy as np


from NeuronNet import *


net = NeuronNet()


learn_inputs = np.array([[1, 0], [0, 0], [0, 1]])
learn_answers = np.array([1, 0, 0])


net.learn(learn_inputs, learn_answers)


x = np.array([1, 1])


if (net.activate(x) < 0.5):
print("0")
else:
print("1")
Natija: