Build a simple neural network using TensorFlow.

Building a simple neural network in TensorFlow can be broken down into the following steps:

1. Import the necessary libraries:

import tensorflow as tf

1. Prepare the data.

# 定义输入特征和标签
X = tf.constant([[0.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 1.0]], dtype=tf.float32)
y = tf.constant([[0.0], [1.0], [1.0], [0.0]], dtype=tf.float32)

1. Model definition:

# 定义神经网络模型
model = tf.keras.Sequential([
    tf.keras.layers.Dense(2, activation='relu', input_shape=(2,)),
    tf.keras.layers.Dense(1, activation='sigmoid')
])

1. Compile model:

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

1. Training model:

model.fit(X, y, epochs=1000)

1. Make predictions using the model.

predictions = model.predict(X)
print(predictions)

By following the steps above, you can build a simple neural network model in TensorFlow, train and predict data. You can adjust the structure and parameters of the model based on specific problem requirements to improve performance and accuracy.