Content deleted Content added
No edit summary |
m link text mining using Find link |
||
Line 37:
===Replicated Softmax Model===
The '''Replicated Softmax Model'''<ref>{{cite web |url=http://papers.nips.cc/paper/3856-replicated-softmax-an-undirected-topic-model.pdf|title=Replicated Softmax Model |year=2009a}}</ref> is also an variant of restricted Boltzmann machine and commonly used to model word count vectors in a document. In a typical [[text mining]] problem, let <math>K</math> be the dictionary size, and <math>M</math> be the number of words in the document. Let <math>\mathbf V</math> be a <math>M \times K</math> binary matrix with <math>v_{ik} = 1</math> only when the <math>i^{th}</math> word in the document is the <math>k^{th}</math> word in the dictionary. <math>\hat v_k</math> denotes the count for the <math>k^{th}</math> word in the dictionary. The energy of the state <math>\{\mathbf V,\mathbf h\}</math> for a document contains <math>M</math> words is defined as
:<math>E(\mathbf V,\mathbf h) = -\sum_{j=1}^{F}\sum_{k=1}^{K}W_{jk}\hat v_kh_j - \sum_{k=1}^Kb_k\hat v_k - M\sum_{j=1}^{F}a_jh_j</math>
The conditional distributions are given by
| |||