Conversazione# Sun'iy neyron tarmog'ini yaratish uchun TensorFlow kutubxonasidan foydalanamiz.

# Sun'iy neyron tarmog'ini yaratish uchun TensorFlow kutubxonasidan foydalanamiz. import tensorflow as tf from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Dense from sklearn.datasets import make_moons from sklearn.model_selection import train_test_split from sklearn.preprocessing import StandardScaler import matplotlib.pyplot as plt # 1. Ma'lumotlar tayyorlash # "make_moons" funksiyasi sun'iy ma'lumotlar to'plamini yaratadi X, y = make_moons(n_samples=1000, noise=0.2, random_state=42) # Ma'lumotlarni trening va test to'plamlariga ajratish X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) # Ma'lumotlarni standartlashtirish scaler = StandardScaler() X_train = scaler.fit_transform(X_train) X_test = scaler.transform(X_test) # 2. Model yaratish model = Sequential([ Dense(16, activation='relu', input_shape=(2,)), # 1-qavat: 16 neyron, ReLU faollashtirish funksiyasi Dense(16, activation='relu'), # 2-qavat: 16 neyron, ReLU Dense(1, activation='sigmoid') # 3-qavat (chiqish qavati): 1 neyron, Sigmoid funksiyasi ]) # Modelni kompilyatsiya qilish model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy']) # 3. Modelni o'qitish history = model.fit(X_train, y_train, epochs=50, batch_size=32, validation_split=0.2, verbose=1) # 4. Modelni baholash test_loss, test_accuracy = model.evaluate(X_test, y_test) print(f"Test to'plamidagi aniqlik: {test_accuracy:.2f}") # 5. Natijalarni vizualizatsiya qilish # O'qitish jarayonidagi yo'qotish va aniqlikni chizish plt.figure(figsize=(12, 5)) # Yo'qotish grafigi plt.subplot(1, 2, 1) plt.plot(history.history['loss'], label='Trening yo\'qotish') plt.plot(history.history['val_loss'], label='Validatsiya yo\'qotish') plt.title('Yo\'qotish') plt.xlabel('Epochs') plt.ylabel('Yo\'qotish') plt.legend() # Aniqlik grafigi plt.subplot(1, 2, 2) plt.plot(history.history['accuracy'], label='Trening aniqlik') plt.plot(history.history['val_accuracy'], label='Validatsiya aniqlik') plt.title('Aniqlik') plt.xlabel('Epochs') plt.ylabel('Aniqlik') plt.legend() plt.show()