从自我学习到深层网络

From Ufldl

Jump to: navigation, search
Line 28: Line 28:
【原文】
【原文】
We are interested in solving a classification task, where our goal is to predict labels <math>\textstyle y</math>.  We have a labeled training set <math>\textstyle \{ (x_l^{(1)}, y^{(1)}), (x_l^{(2)}, y^{(2)}), \ldots (x_l^{(m_l)},y^{(m_l)}) \}</math> of <math>\textstyle m_l</math> labeled examples. We showed previously that we can replace the original features <math>\textstyle x^{(i)}</math> with features <math>\textstyle a^{(l)}</math> computed by the sparse autoencoder (the "replacement" representation).  This gives us a training set <math>\textstyle \{(a^{(1)},y^{(1)}), \ldots (a^{(m_l)}, y^{(m_l)}) \}</math>.  Finally, we train a logistic classifier to map from the features <math>\textstyle a^{(i)}</math> to the classification label <math>\textstyle y^{(i)}</math>. To illustrate this step, similar to [[Neural Networks|our earlier notes]], we can draw our logistic regression unit (shown in orange) as follows:
We are interested in solving a classification task, where our goal is to predict labels <math>\textstyle y</math>.  We have a labeled training set <math>\textstyle \{ (x_l^{(1)}, y^{(1)}), (x_l^{(2)}, y^{(2)}), \ldots (x_l^{(m_l)},y^{(m_l)}) \}</math> of <math>\textstyle m_l</math> labeled examples. We showed previously that we can replace the original features <math>\textstyle x^{(i)}</math> with features <math>\textstyle a^{(l)}</math> computed by the sparse autoencoder (the "replacement" representation).  This gives us a training set <math>\textstyle \{(a^{(1)},y^{(1)}), \ldots (a^{(m_l)}, y^{(m_l)}) \}</math>.  Finally, we train a logistic classifier to map from the features <math>\textstyle a^{(i)}</math> to the classification label <math>\textstyle y^{(i)}</math>. To illustrate this step, similar to [[Neural Networks|our earlier notes]], we can draw our logistic regression unit (shown in orange) as follows:
 +
 +
【初译】
 +
我们感兴趣的是解决一个分类任务,目标是预测样本类型<math>\textstyle y</math>。我们拥有标注数据集<math>\textstyle \{ (x_l^{(1)}, y^{(1)}), (x_l^{(2)}, y^{(2)}), \ldots (x_l^{(m_l)},y^{(m_l)}) \}</math>,包含<math>\textstyle m_l</math>个标注样本。此前我们已经证明,可以利用稀疏自动编码机计算获得的特征<math>\textstyle a^{(l)}</math> (“替代”表示)来替代初始特征<math>\textstyle x^{(i)}</math>。如此,我们就获得训练数据集<math>\textstyle \{(a^{(1)},y^{(1)}), \ldots (a^{(m_l)}, y^{(m_l)}) \}</math>。最终,我们训练得到一个从特征<math>\textstyle a^{(i)}</math> 到分类标注<math>\textstyle y^{(i)}</math>的logistic分类器。为说明这一过程,如同我们此前的笔记,可以如下图描述logistic回归单元(橘黄色)。
 +
 +
【一审】
 +
我们感兴趣的是解决一个分类任务,目标是预测标注类型<math>\textstyle y</math>。我们拥有标注训练集<math>\textstyle \{ (x_l^{(1)}, y^{(1)}), (x_l^{(2)}, y^{(2)}), \ldots (x_l^{(m_l)},y^{(m_l)}) \}</math>,包含math>\textstyle m_l</math>个标注样本。此前我们已经证明,可以利用稀疏自动编码器计算获得的特征<math>\textstyle a^{(l)}</math>(“替代”表示)来替代初始特征。如此,我们就获得训练数据集<math>\textstyle \{(a^{(1)},y^{(1)}), \ldots (a^{(m_l)}, y^{(m_l)}) \}</math>。最终,我们训练得到一个从特征<math>\textstyle a^{(i)}</math> 到分类标注<math>\textstyle y^{(i)}</math>的logistic分类器。为说明这一过程,如同我们此前的笔记,可以如下图描述logistic回归单元(橘黄色)。

Revision as of 07:27, 13 March 2013

Personal tools