Topologically ordered feature extraction based on sparse group restricted Boltzmann machines (Q1665138): Difference between revisions
From MaRDI portal
Set OpenAlex properties. |
ReferenceBot (talk | contribs) Changed an Item |
||
Property / cites work | |||
Property / cites work: Training Products of Experts by Minimizing Contrastive Divergence / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Reducing the Dimensionality of Data with Neural Networks / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Training restricted Boltzmann machines: an introduction / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: A Fast Learning Algorithm for Deep Belief Nets / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Justifying and Generalizing Contrastive Divergence / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Learning Deep Architectures for AI / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Q3093232 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Comparing Measures of Sparsity / rank | |||
Normal rank |
Latest revision as of 11:43, 16 July 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Topologically ordered feature extraction based on sparse group restricted Boltzmann machines |
scientific article |
Statements
Topologically ordered feature extraction based on sparse group restricted Boltzmann machines (English)
0 references
27 August 2018
0 references
Summary: How to extract topologically ordered features efficiently from high-dimensional data is an important problem of unsupervised feature learning domains for deep learning. To address this problem, we propose a new type of regularization for Restricted Boltzmann Machines (RBMs). Adding two extra terms in the log-likelihood function to penalize the group weights and topologically ordered factors, this type of regularization extracts topologically ordered features based on sparse group Restricted Boltzmann Machines (SGRBMs). Therefore, it encourages an RBM to learn a much smoother probability distribution because its formulations turn out to be a combination of the group weight-decay and topologically ordered factor regularizations. We apply this proposed regularization scheme to image datasets of natural images and Flying Apsara images in the Dunhuang Grotto Murals at four different historical periods. The experimental results demonstrate that the combination of these two extra terms in the log-likelihood function helps to extract more discriminative features with much sparser and more aggregative hidden activation probabilities.
0 references