稀疏编码自编码表达

From Ufldl

Jump to: navigation, search
([良好的s初始值])
Line 120: Line 120:
无疑,这样的初始化有助于算法的改进,因为上述的第一步希望找到满足<math>Ws \approx x</math>的矩阵<math>s</math>;第二步对<math>s</math>作规范化处理是为了保持较小的稀疏惩罚值。这也表明,只采用上述步骤的某一步而不是两步对<math>s</math>做初始化处理将严重影响算法性能。 (TODO:此链接将会对为什么这样的初始化能改进算法作出更详细的解释)
无疑,这样的初始化有助于算法的改进,因为上述的第一步希望找到满足<math>Ws \approx x</math>的矩阵<math>s</math>;第二步对<math>s</math>作规范化处理是为了保持较小的稀疏惩罚值。这也表明,只采用上述步骤的某一步而不是两步对<math>s</math>做初始化处理将严重影响算法性能。 (TODO:此链接将会对为什么这样的初始化能改进算法作出更详细的解释)
-
Very roughly and informally speaking, this initialization helps because the first step is an attempt to find a good <math>s</math> such that <math>Ws \approx x</math>, and the second step "normalizes" <math>s</math> in an attempt to keep the sparsity penalty small. It turns out that initializing <math>s</math> using only one but not both steps results in poor performance in practice. ([[TODO]]: a better explanation for why this initialization helps?)
 
-
 
-
[原文]
 
=== The practical algorithm[可运行算法] ===
=== The practical algorithm[可运行算法] ===

Revision as of 07:07, 21 March 2013

Personal tools