Yakagadziriswa: kuronga neural network

Kuvaka neural network modhi inzvimbo inonakidza mukudzidza kwemichina, kunyanya muPython. Inopa yakakura chiyero chekuongorora, kufanotaura, uye otomatiki maitiro ekuita sarudzo. Tisati tanyura mune nitty-gritty yekuvaka chirongwa neural network, zvakakosha kuti tinzwisise kuti neural network chii. Yakanyanya sisitimu yealgorithms inobatisisa chimiro chehuropi hwemunhu, nekudaro ichigadzira artificial neural network iyo, kuburikidza nekuongorora maitiro inodudzira data rekunzwa, kutora pane nuances 'zvisingaonekwe' neiyo mbishi data, sezvinoita uropi hwedu.

A neural network yakakosha mukuita zvekuchera data, kwainotaridza mapatani nemafambiro anga akanyanya kuomarara kune vanhu kana mamwe maitiro emakombuta. Zvino, ngatinyure mukati memoyo wenyaya- tichishandisa Python kuvaka uye kuronga neural network.

Kuronga neural network muPython

# Importing libraries
import numpy as np     
import matplotlib.pyplot as plt     
from sklearn.datasets import make_blobs 

# Create a sample dataset
dataset=make_blobs(n_samples=800, centers=2, n_features=2, cluster_std=1.6, random_state=50)

# Split into input (X) and output (y)
X, y = dataset

# Plot the sample data
plt.scatter(X[:,0], X[:,1], c=y)
plt.show()

Ngatinzwisise kodhi iyi:

  • Mumitsara mina yekutanga, tinopinza maraibhurari anodiwa senge numpy, matplotlib nezvimwe.
  • Tevere, tichishandisa iyo 'make_blobs' basa kubva sklearn, tinogadzira dataset.
  • Ipapo iyo dataset inokamurwa kuita zvekupinza (X) uye zvinobuda (y).
  • Mutsetse wekupedzisira unoronga X uye y uye unotipa tarisiro yedata uchishandisa basa rekuparadzira kubva kuraibhurari yematplotlib.

Kunzwisisa chirongwa neural network library

Kunzwisisa maraibhurari ePython mune ino mamiriro kwakakosha. Iyo numpy raibhurari inobvumira mashandiro emasvomhu, matplotlib inoshandiswa 2D graph kuronga kubva kudhata iri muPython uye sklearn spearheads muchina kudzidza muPython.

Iyo nhanho-ne-nhanho kodhi

Nhanho-ne-nhanho maitiro ekodhi inotibvumira kuwana nzwisiso yakadzama:

# Import necessary modules
from keras.models import Sequential
from keras.layers import Dense

# Create the model
model = Sequential()

# Add input layer with 2 inputs neurons
model.add(Dense(input_dim=2, output_dim=1, init='uniform', activation='sigmoid'))

# Compile model
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

# Fit the model
history = model.fit(X, y, epochs=100, batch_size=10)

Muchikamu ichi chekodhi,

  • Isu tinogadzira modhi tichishandisa Sequential () basa kubva keras.models module.
  • Tevere, mupendero wekuisa unowedzerwa ne 2 neurons yekupinza. Pano, 'Dense' imhando yemhando inoshanda kune mazhinji kesi. Mune dense layer, ma node ese ari mumashure mekare anobatana nemanodhi ari muchikamu chazvino.
  • 'Kuunganidza' kunogadzirira modhi yekudzidziswa.
  • Chikamu chekupedzisira, 'kukodzera modhi' ndiko kunodzidziswa neural network. 'Epochs' inoratidza huwandu hwekupasa kwese dataset yekudzidziswa. Iyo modhi inodzidza uye inogadziridza modhi paramita panguva yega yega. Saizi yebatch ichikamu che dataset.

Kuburikidza nemakodhi aya, tinovaka hwaro hwekugadzira chirongwa neural network uchishandisa Python. Nemaraibhurari ePython akakura uye masimba ane simba, neural network inogona kuitwa uye kuoneswa zvinobudirira. Ingori nezvekunzwisisa midzi, uye iwe wakanaka kukura mundima iyi inosiyana-siyana yekudzidza kwemichina.

Related posts:

Leave a Comment