如何使Keras神经网络在Iris d上表现优于Logistic回归

Question

我在比较Keras神经网络和简单的虹膜数据Logistic Regression from Scikit-learn。我希望Keras NN的性能会更好，正如this post所建议的那样。在

但是为什么通过模拟那里的代码，Keras NN的结果比 逻辑回归？在

import seaborn as sns
import numpy as np
from sklearn.cross_validation import train_test_split
from sklearn.linear_model import LogisticRegressionCV
from keras.models import Sequential
from keras.layers.core import Dense, Activation
from keras.utils import np_utils

# Prepare data
iris = sns.load_dataset("iris")
X = iris.values[:, 0:4]
y = iris.values[:, 4]

# Make test and train set
train_X, test_X, train_y, test_y = train_test_split(X, y, train_size=0.5, random_state=0)

################################
# Evaluate Logistic Regression
################################
lr = LogisticRegressionCV()
lr.fit(train_X, train_y)
pred_y = lr.predict(test_X)
print("Test fraction correct (LR-Accuracy) = {:.2f}".format(lr.score(test_X, test_y)))



################################
# Evaluate Keras Neural Network
################################

# Make ONE-HOT
def one_hot_encode_object_array(arr):
    '''One hot encode a numpy array of objects (e.g. strings)'''
    uniques, ids = np.unique(arr, return_inverse=True)
    return np_utils.to_categorical(ids, len(uniques))


train_y_ohe = one_hot_encode_object_array(train_y)
test_y_ohe = one_hot_encode_object_array(test_y)

model = Sequential()
model.add(Dense(16, input_shape=(4,)))
model.add(Activation('sigmoid'))
model.add(Dense(3))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='adam')

# Actual modelling
model.fit(train_X, train_y_ohe, verbose=0, batch_size=1)
score, accuracy = model.evaluate(test_X, test_y_ohe, batch_size=16, verbose=0)
print("Test fraction correct (NN-Score) = {:.2f}".format(score))
print("Test fraction correct (NN-Accuracy) = {:.2f}".format(accuracy))

我用的是这个版本的Keras

^{pr2}$

结果表明：

Test fraction correct (LR-Accuracy) = 0.83
Test fraction correct (NN-Score) = 0.75
Test fraction correct (NN-Accuracy) = 0.60

根据that post，Keras的准确度应为0.99。出什么问题了？在

Answer 1

你的神经网络很简单。尝试通过添加更多的神经元和层来创建深层神经网络。此外，缩放功能也很重要。尝试glorot_uniform初始值设定项。最后但并非最不重要的是，增加历元，看看损失是否随着历元的增加而减少。在

所以给你：

model = Sequential()
model.add(Dense(input_dim=4, output_dim=512, init='glorot_uniform'))
model.add(PReLU(input_shape=(512,)))
model.add(BatchNormalization((512,)))
model.add(Dropout(0.5))

model.add(Dense(input_dim=512, output_dim=512, init='glorot_uniform'))
model.add(PReLU(input_shape=(512,)))
model.add(BatchNormalization((512,)))
model.add(Dropout(0.5))

model.add(Dense(input_dim=512, output_dim=512, init='glorot_uniform'))
model.add(PReLU(input_shape=(512,)))
model.add(BatchNormalization((512,)))
model.add(Dropout(0.5))

model.add(Dense(input_dim=512, output_dim=512, init='glorot_uniform'))
model.add(PReLU(input_shape=(512,)))
model.add(BatchNormalization((512,)))
model.add(Dropout(0.5))

model.add(Dense(input_dim=512, output_dim=512, init='glorot_uniform'))
model.add(PReLU(input_shape=(512,)))
model.add(BatchNormalization((512,)))
model.add(Dropout(0.5))

model.add(Dense(input_dim=512, output_dim=3, init='glorot_uniform'))
model.add(Activation('softmax'))

这在公元120年达到了0.97左右

Answer 2

在本月（2016年4月）刚刚发布的Keras版本1中，默认的epoch数量从Keras版本0中的100减少到10个。尝试：

model.fit(train_X, train_y_ohe, verbose=0, batch_size=1, nb_epoch=100)