稀疏编码自编码表达

From Ufldl

Revision as of 04:59, 7 March 2013 (view source) Kandeng (Talk | contribs) (Created page with "稀疏编码: 自编码表达") ← Older edit		Revision as of 04:56, 8 March 2013 (view source) Kandeng (Talk | contribs) Newer edit →
Line 1:		Line 1:
-	稀疏编码: 自编码表达	+	[原文]
		+	== Sparse coding [稀疏编码]==
		+
		+	In the sparse autoencoder, we tried to learn a set of weights W (and associated biases b) that would give us sparse features σ(Wx + b) useful in reconstructing the input x.
		+
		+	[初译]
		+
		+	稀疏编码
		+
		+	在稀疏自编码中，为了用稀疏特征σ(Wx + b)重新表示输入数据X需要学习权重系数W（以及对应的偏移量b）。
		+
		+	[一审]
		+
		+	稀疏编码
		+
		+	在稀疏自编码中，为了用稀疏特征σ(Wx + b)重新表示输入数据X需要学习权重系数W（以及对应的偏移量b）。
		+
		+	[[File:Sparse coding.png | 400px]]
		+
		+	[原文]
		+
		+	Sparse coding can be seen as a modification of the sparse autoencoder method in which we try to learn the set of features for some data "directly". Together with an associated basis for transforming the learned features from the feature space to the data space, we can then reconstruct the data from the learned features.
		+
		+	[初译]
		+
		+	稀疏编码可以看作是稀疏自编码方法的一个变形，该方法试图直接学习数据的特征集。利用偏移量将待学习特征集从特征空间转化到数据空间，实现了待学习特征集数据的重新表示。
		+
		+	[一审]
		+
		+	稀疏编码可以看作是稀疏自编码方法的一个变形，该方法试图直接学习数据的特征集。利用连带基将学习特征集从特征空间转化到数据空间，就可以从学到的特征中重建数据。
		+
		+	[原文]
		+
		+	Formally, in sparse coding, we have some data x we would like to learn features on. In particular, we would like to learn s, a set of sparse features useful for representing the data, and A, a basis for transforming the features from the feature space to the data space. Our objective function is hence:
		+	<math>F(A; s) = \lVert As - x \rVert_2^2 + \gamma \lVert A \rVert_2^2</math>
		+
		+
		+	[初译]
		+
		+	在稀疏编码中，通常有很多数据x供我们进行特征学习。例如：s是一个用于表示数据的稀疏特征集，A是特征集从特征空间转换到数据空间的基。因此，为了计算s和A构建如下目标函数：
		+
		+	[一审]
		+
		+	在稀疏编码中，对于从数据x中进行特征学习的情况。例如学习一个用于表示数据的稀疏特征集s，和一个将特征从特征空间转换到数据空间的基A,我们可以构建如下目标函数：

---

Revision as of 04:56, 8 March 2013