scholarly journals Skull segmentation from MR scans using a higher-order shape model based on convolutional restricted Boltzmann machines

2018 ◽  
Author(s):  
Koen Van Leemput ◽  
Jesper D. Nielsen ◽  
Christian Bauer ◽  
Hartwig Siebner ◽  
Kristoffer H. Madsen ◽  
...  
Keyword(s):  
Higher Order ◽  
Restricted Boltzmann Machines ◽  
Shape Model ◽  
Boltzmann Machines ◽  
Model Based

Using Conditional Restricted Boltzmann Machines to Model Complex Consumer Shopping Patterns

2019 ◽  
Vol 38 (4) ◽  
pp. 711-727 ◽  
Author(s):  
Feihong Xia ◽  
Rabikar Chatterjee ◽  
Jerrold H. May
Keyword(s):  
Data Sets ◽  
Restricted Boltzmann Machines ◽  
Boltzmann Machines ◽  
Model Based ◽  
Model Complex ◽  
Purchase Patterns

We develop and apply a model based on conditional restricted Boltzmann machines to analyze intertemporal crossproduct purchase patterns in enormous consumer purchase data sets.

scholarly journals Shape Modeling Based on Convolutional Restricted Boltzmann Machines

2018 ◽  
Vol 173 ◽  
pp. 01022
Author(s):  
Xi-Li Wang ◽  
Fen Chen
Keyword(s):  
Euclidean Distance ◽  
Shape Modeling ◽  
Test Time ◽  
Construction Process ◽  
Restricted Boltzmann Machines ◽  
Shape Model ◽  
Training Time ◽  
Boltzmann Machines ◽  
The Difference ◽  
And Training

This paper proposes a kind of shape model based on convolutional restricted Boltzmann machines(CRBM), which can be used to assist the task of image target detection and classification. The CRBM is a generative model that can model shapes through the generative capabilities of the model. This paper presents the visual representation, construction process and training method of the model construction. This paper does experiments on the Weizmann Horse dataset. The results show that, compared with RBM, although the training time of this model is slightly longer, the test time of the model is similar, and it can better shape modeling, modeling of the details of the shape can be well expressed. The samples generated from CRBM look more realistic. The difference between the shape and the original shape generated by Euclidean distance measurement shows that the model has a strong ability to model shapes.

scholarly journals Adaptive hyperparameter updating for training restricted Boltzmann machines on quantum annealers

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Guanglei Xu ◽  
William S. Oates
Keyword(s):  
Neural Network ◽  
Maximum Likelihood ◽  
Image Reconstruction ◽  
Image Recognition ◽  
Shannon Entropy ◽  
Reconstruction Error ◽  
Likelihood Method ◽  
Restricted Boltzmann Machines ◽  
Boltzmann Machines ◽  
D Wave

AbstractRestricted Boltzmann Machines (RBMs) have been proposed for developing neural networks for a variety of unsupervised machine learning applications such as image recognition, drug discovery, and materials design. The Boltzmann probability distribution is used as a model to identify network parameters by optimizing the likelihood of predicting an output given hidden states trained on available data. Training such networks often requires sampling over a large probability space that must be approximated during gradient based optimization. Quantum annealing has been proposed as a means to search this space more efficiently which has been experimentally investigated on D-Wave hardware. D-Wave implementation requires selection of an effective inverse temperature or hyperparameter ($$\beta $$ β ) within the Boltzmann distribution which can strongly influence optimization. Here, we show how this parameter can be estimated as a hyperparameter applied to D-Wave hardware during neural network training by maximizing the likelihood or minimizing the Shannon entropy. We find both methods improve training RBMs based upon D-Wave hardware experimental validation on an image recognition problem. Neural network image reconstruction errors are evaluated using Bayesian uncertainty analysis which illustrate more than an order magnitude lower image reconstruction error using the maximum likelihood over manually optimizing the hyperparameter. The maximum likelihood method is also shown to out-perform minimizing the Shannon entropy for image reconstruction.

A note on design-based versus model-based variance estimation in stereology

2002 ◽  
Vol 34 (03) ◽  
pp. 484-490 ◽  
Author(s):  
Asger Hobolth ◽  
Eva B. Vedel Jensen
Keyword(s):  
Mathematical Model ◽  
Original Problem ◽  
Variance Estimation ◽  
Point Of View ◽  
Systematic Sampling ◽  
Variance Estimator ◽  
Shape Model ◽  
Model Based ◽  
Versus Model ◽  
Special Case

Recently, systematic sampling on the circle and the sphere has been studied by Gual-Arnau and Cruz-Orive (2000) from a design-based point of view. In this note, it is shown that their mathematical model for the covariogram is, in a model-based statistical setting, a special case of the p-order shape model suggested by Hobolth, Pedersen and Jensen (2000) and Hobolth, Kent and Dryden (2002) for planar objects without landmarks. Benefits of this observation include an alternative variance estimator, applicable in the original problem of systematic sampling. In a wider perspective, the paper contributes to the discussion concerning design-based versus model-based stereology.

Sign in / Sign up

Export Citation Format

Share Document