我目前正在使用tensorflow的新keras API开展一个小型二元分类项目。该问题是Kaggle.com几年前发布的Higgs Boson挑战赛的简化版本。数据集的形状为2000x14，其中每行的前13个元素构成输入向量，第14个元素是相应的标签。以下是所述数据集的样本：
86.043,52.881,61.231,95.475,0.273,77.169,-0.015,1.856,32.636,202.068, 2.432,-0.419,0.0,0
138.149,69.197,58.607,129.848,0.941,120.276,3.811,1.886,71.435,384.916,2.447,1.408,0.0,1
137.457,3.018,74.670,81.705,5.954,775.772,-8.854,2.625,1.942,157.231,1.193,0.873,0.824,1
我对机器学习和tensorflow比较新，但熟悉损失函数、优化器和激活函数等高级概念。我尝试根据网上找到的二元分类问题示例构建各种模型，但训练模型时遇到了困难。在训练过程中，有时损失会在同一轮内增加，导致学习不稳定。准确率在70%左右停滞不前。我尝试改变学习率和其他超参数，但无济于事。与此相比，我已经硬编码了一个完全连接的前馈神经网络，在同样的问题上达到了80-85%的准确率。
这是我的当前模型：
import tensorflow as tf
from tensorflow.python.keras.layers.core import Dense
import numpy as np
import pandas as pd
def normalize(array):
return array/np.linalg.norm(array, ord=2, axis=1, keepdims=True)
x_train = pd.read_csv('data/labeled.csv', sep='\s+').iloc[:1800, :-1].values
y_train = pd.read_csv('data/labeled.csv', sep='\s+').iloc[:1800, -1:].values
x_test = pd.read_csv('data/labeled.csv', sep='\s+').iloc[1800:, :-1].values
y_test = pd.read_csv('data/labeled.csv', sep='\s+').iloc[1800:, -1:].values
x_train = normalize(x_train)
x_test = normalize(x_test)
model = tf.keras.Sequential()
model.add(Dense(9, input_dim=13, activation=tf.nn.sigmoid)
model.add(Dense(6, activation=tf.nn.sigmoid))
model.add(Dense(1, activation=tf.nn.sigmoid))
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
model.fit(x_train, y_train, epochs=50)
model.evaluate(x_test, y_test)
正如提到的那样，一些时代的起始准确性高于结束准确性，导致学习不稳定。
32/1800 [..............................] - ETA: 0s - loss: 0.6830 - acc: 0.5938
1152/1800 [==================>...........] - ETA: 0s - loss: 0.6175 - acc: 0.6727
1800/1800 [==============================] - 0s 52us/step - loss: 0.6098 - acc: 0.6861
Epoch 54/250
32/1800 [..............................] - ETA: 0s - loss: 0.5195 - acc: 0.8125
1376/1800 [=====================>........] - ETA: 0s - loss: 0.6224 - acc: 0.6672
1800/1800 [==============================] - 0s 43us/step - loss: 0.6091 - acc: 0.6850
Epoch 55/250
编辑：
我已经根据评论中的建议对模型进行了一些修改。它现在看起来更像这样：
model = tf.keras.Sequential()
model.add(Dense(250, input_dim=13, activation=tf.nn.relu))
model.add(Dropout(0.4))
model.add(Dense(200, activation=tf.nn.relu))
model.add(Dropout(0.4))
model.add(Dense(100, activation=tf.nn.relu))
model.add(Dropout(0.3))
model.add(Dense(50, activation=tf.nn.relu))
model.add(Dense(1, activation=tf.nn.sigmoid))
model.compile(optimizer='adadelta',
loss='binary_crossentropy',
metrics=['accuracy'])