Sparse Coding

From Ufldl

Jump to: navigation, search
(Created page with "== Background and Motivation == Sparse coding is a class of unsupervised methods for learning sets of over-complete bases to represent data efficiently. The aim of sparse coding ...")
Line 37: Line 37:
Assuming <math>\nu</math> is Gaussian white noise with variance <math>\sigma^2</math>, we have that  
Assuming <math>\nu</math> is Gaussian white noise with variance <math>\sigma^2</math>, we have that  
:<math>\begin{align}
:<math>\begin{align}
-
P(\mathbf{x} \mid \mathbf{a}, \mathbf{\phi}) = \frac^{1}_{Z} \exp(- \frac^{1}_{2\sigma^2})
+
P(\mathbf{x} \mid \mathbf{a}, \mathbf{\phi}) = \frac{1}{Z} \exp(- \frac{\mathbf{x}-\sum^{k}_{i=1} a_i \mathbf{\phi}_{i} }{2\sigma^2})
\end{align}</math>
\end{align}</math>
In order to define the distribution <math>P(\mathbf{x}\mid\mathbf{\phi})</math>, we must first specify a prior distribution over the amplitudes <math>a_i</math>
In order to define the distribution <math>P(\mathbf{x}\mid\mathbf{\phi})</math>, we must first specify a prior distribution over the amplitudes <math>a_i</math>

Revision as of 11:20, 21 March 2011

Personal tools