第一章

1. 人工智能、机器学习、深度学习之间的关系

2. 人工智能：将通常由人类完成的智力任务自动化。

3. 机器学习

第二章

keras实现mnist识别

from keras.datasets import mnist
from keras import models
from keras import layers
from keras.utils import to_categorical
import numpy as np


def load_data():
    (train_images, train_labels), (test_images, test_labels) = mnist.load_data()

    train_images = train_images.reshape((60000, 28 * 28))
    train_images = train_images.astype(np.float32) / 255

    test_images = test_images.reshape((10000, 28 * 28))
    test_images = test_images.astype(np.float32) / 255

    train_labels = to_categorical(train_labels)

    test_labels = to_categorical(test_labels)

    return (train_images, train_labels), (test_images, test_labels)


(x_train, y_train), (x_test, y_test) = load_data()

network = models.Sequential()
network.add(layers.Dense(units=512, activation='relu', input_shape=(28 * 28,)))
network.add(layers.Dense(units=10, activation='softmax'))

network.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])

network.fit(x=x_train, y=y_train, batch_size=128, epochs=5)

test_loss, test_acc = network.evaluate(x=x_test, y=y_test)

print(network.summary())
print('test_acc:', test_acc)
print('test_loss:', test_loss)