TensorFlow ile Doğrusal Regresyon

import numpy as np
import tensorflow as tf

# Veri seti (örnek)
X = np.array([1, 2, 3, 4, 5], dtype=np.float32)  # Girdi
y = np.array([2, 4, 6, 8, 10], dtype=np.float32)  # Çıktı (2x ilişkisi)

# Model parametreleri
w = tf.Variable(0.0)  # Ağırlık
b = tf.Variable(0.0)  # Bias

# Doğrusal model
def linear_model(X):
    return w * X + b

# Kayıp fonksiyonu (Mean Squared Error)
def loss_fn(y_true, y_pred):
    return tf.reduce_mean(tf.square(y_true - y_pred))

# Optimizasyon (Gradient Descent Optimizer)
optimizer = tf.optimizers.SGD(learning_rate=0.01)

# Modeli eğit
for epoch in range(1000):
    with tf.GradientTape() as tape:
        y_pred = linear_model(X)
        loss = loss_fn(y, y_pred)
    
    gradients = tape.gradient(loss, [w, b])
    optimizer.apply_gradients(zip(gradients, [w, b]))

print(f"Öğrenilen ağırlık (w): {w.numpy()}, Bias (b): {b.numpy()}")

# Modelin tahminleri
y_pred = linear_model(X)
print("Tahminler:", y_pred.numpy())