Difference between revisions of "Restricted Boltzmann machine"
(Created page with "A '''restricted Boltzmann machine''', commonly abbreviated as '''RBM''', is a neural network where neurons beyond the visible have probabilitistic outputs. The machine is rest...") |
(→Model) |
||
| Line 26: | Line 26: | ||
<center><math> P \left ( x'_i=1 \right ) = \varphi \left ( \sum_j y_j w_{ij} \right )</math></center> | <center><math> P \left ( x'_i=1 \right ) = \varphi \left ( \sum_j y_j w_{ij} \right )</math></center> | ||
| − | To update the weights, a set of inputs are presented, the outputs generated, and the inputs reconstructed. Then an average is taken over the results, and the weights are updated as follows: | + | To update the weights, a set of inputs are presented, the outputs generated, and the inputs reconstructed. In practice, the reconstruction is then fed back to the input layer and another cycle is run, for several cycles, which is known as ''Gibbs sampling''. Then an average is taken over the results, and the weights are updated as follows: |
<center><math>\Delta w_{ij} = \eta \left ( \langle x_i y_j \rangle_N - \langle x'_i y_j \rangle_N \right )</math></center> | <center><math>\Delta w_{ij} = \eta \left ( \langle x_i y_j \rangle_N - \langle x'_i y_j \rangle_N \right )</math></center> | ||
| − | where <math>\eta</math> is some learning rate and the subscript <math>N</math> indicates that the average is taken over <math>N</math> input presentations | + | where <math>\eta</math> is some learning rate and the subscript <math>N</math> indicates that the average is taken over <math>N</math> input presentations. |
Revision as of 18:15, 24 April 2012
A restricted Boltzmann machine, commonly abbreviated as RBM, is a neural network where neurons beyond the visible have probabilitistic outputs. The machine is restricted because connections are restricted to be from one layer to the next, that is, having no intra-layer connections.
Model
We use a set of binary-valued neurons. Given a set of k-dimensional inputs represented as a column vector <math>\vec{x} = [x_1, x_2, \cdots, x_k]^T</math>, and a set of m neurons with (initially random, between -0.01 and 0.01) synaptic weights from the inputs, represented as a matrix formed by m weight column vectors (i.e. a k row x m column matrix):
w_{11} & w_{12} & \cdots & w_{1m}\\ w_{21} & w_{22} & \cdots & w_{2m}\\ \vdots & & & \vdots \\ w_{k1} & w_{m2} & \cdots & w_{km}
\end{bmatrix}</math>where <math>w_{ij}</math> is the weight between input i and neuron j, the output of the set of neurons is defined as follows:
where <math>\varphi \left ( \cdot \right )</math> is the logistic sigmoidal function:
From this output, a binary-valued reconstruction of the input <math>\vec{x'}</math> is formed as follows:
To update the weights, a set of inputs are presented, the outputs generated, and the inputs reconstructed. In practice, the reconstruction is then fed back to the input layer and another cycle is run, for several cycles, which is known as Gibbs sampling. Then an average is taken over the results, and the weights are updated as follows:
where <math>\eta</math> is some learning rate and the subscript <math>N</math> indicates that the average is taken over <math>N</math> input presentations.
