# 独立成分分析

(Difference between revisions)
 Revision as of 04:36, 8 April 2013 (view source)Kandeng (Talk | contribs)← Older edit Latest revision as of 04:37, 8 April 2013 (view source)Kandeng (Talk | contribs) Line 73: Line 73: ==中英文对照== ==中英文对照== - :独立成分分析 Independent Component Analysis + :独立成分分析     Independent Component Analysis - :稀疏编码算法 Sparse coding + :稀疏编码算法     Sparse coding - :超完备基     Over-complete basis + :超完备基         Over-complete basis - :标准正交基   Orthonormal basis + :标准正交基       Orthonormal basis - :稀疏惩罚项   Sparsity penalty + :稀疏惩罚项       Sparsity penalty - :梯度下降法   Gradient descent + :梯度下降法       Gradient descent - :白化         Whitened + :白化             Whitened - :不完备基     Under-complete basis + :不完备基         Under-complete basis - :线搜索算法   Line-search algorithm + :线搜索算法       Line-search algorithm - :拓扑代价项   Topographic cost term + :拓扑代价项       Topographic cost term

## 概述

$J(W) = \lVert Wx \rVert_1$

$\begin{array}{rcl} {\rm minimize} & \lVert Wx \rVert_1 \\ {\rm s.t.} & WW^T = I \\ \end{array}$

## 标准正交ICA

$\begin{array}{rcl} {\rm minimize} & \lVert Wx \rVert_1 \\ {\rm s.t.} & WW^T = I \\ \end{array}$

1. $W \leftarrow W - \alpha \nabla_W \lVert Wx \rVert_1$
2. $W \leftarrow \operatorname{proj}_U W$, 其中U是满足WWT = I的矩阵空间

## 中文译者

Language : English