Gaussian-binary restricted Boltzmann machines for modeling natural image statistics

Melchior, Jan; Wang, Nan; Wiskott, Laurenz

doi:10.1371/journal.pone.0171015

Cited by 31 publications

(18 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is unique to our work, as other works propose unique training methods and models when changing the distribution of the visible units. For example, this can be seen in the modified Hamiltonians used for real-valued data [69,70]. This construction allows us to consider binary, real-valued, and sparse real-valued datasets within the same framework.…”

Section: Discussionmentioning

confidence: 99%

Deterministic and Generalized Framework for Unsupervised Learning with Restricted Boltzmann Machines

Tramel¹,

Gabrié

Manoel³

et al. 2018

Phys. Rev. X

View full text Add to dashboard Cite

Restricted Boltzmann machines (RBMs) are energy-based neural-networks which are commonly used as the building blocks for deep architectures neural architectures. In this work, we derive a deterministic framework for the training, evaluation, and use of RBMs based upon the Thouless-Anderson-Palmer (TAP) mean-field approximation of widely-connected systems with weak interactions coming from spin-glass theory. While the TAP approach has been extensively studied for fullyvisible binary spin systems, our construction is generalized to latent-variable models, as well as to arbitrarily distributed real-valued spin systems with bounded support. In our numerical experiments, we demonstrate the effective deterministic training of our proposed models and are able to show interesting features of unsupervised learning which could not be directly observed with sampling. Additionally, we demonstrate how to utilize our TAP-based framework for leveraging trained RBMs as joint priors in denoising problems.

show abstract

Section: Discussionmentioning

confidence: 99%

Deterministic and Generalized Framework for Unsupervised Learning with Restricted Boltzmann Machines

Tramel¹,

Gabrié

Manoel³

et al. 2018

Phys. Rev. X

View full text Add to dashboard Cite

show abstract

“…DBN is regarded as a multi-layer perceptron neural networks composed of restricted Boltzmann machines (RBMs) [41,42] in the first stage. In Figure 1, each RBM consists of a visible layer (v) and a hidden layer (h…”

Section: Deep Belief Networkmentioning

confidence: 99%

Size and Location Diagnosis of Rolling Bearing Faults: An Approach of Kernel Principal Component Analysis and Deep Belief Network

Huang¹,

Yu²,

Gu³

2021

IJCIS

View full text Add to dashboard Cite

Diagnosing incipient faults of rotating machines is very important for reducing economic losses and avoiding accidents caused by faults. However, diagnoses of locations and sizes of incipient faults are very difficult in a noisy background. In this paper, we propose a fault diagnosis method that combines kernel principal component analysis (KPCA) and deep belief network (DBN) to detect sizes and locations of incipient faults on rolling bearings. Effective information of raw vibration signals processed by KPCA method is used as input signals of the DBN of which weights of the first RBM are initialized by contribution rates of principal components. A DBN with complex structures can be cut into a briefer network by KPCA-DBN model. That model reduces network structure and increases convergence rate. As a result, an average test accuracy by KPCA-DBN can reach 99.1% for identification of 12 labels including incipient faults and the training time is 28s which is half of that by DBN model. The average accuracy of rolling bearing location detection nearly gets to 100% and the average accuracy of fault size detection is above 99%. Compared with SVM, BP, CNN, Deep EMD-PCA, CNN-SVM and DBN, it is found that training time can be shortened and detection accuracy can be improved by KPCA-DBN model. The proposed method is beneficial to realize sizes and locations detection of incipient faults online.

show abstract

“…The literature [7] performed a theoretical analysis on the Gaussian-binary restricted Boltzmann machines (GRBMs) considering the density models. The major part of the research work was to demonstrate that GRBMs could be expressed as a controlled combination of the Gaussians.…”

Section: Related Workmentioning

confidence: 99%

Greedy Learning of Deep Boltzmann Machine (GDBM)’s Variance and Search Algorithm for Efficient Image Retrieval

Ghrabat

Abduljabbar

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Despite extensive research on content-based image retrieval, challenges such as low accuracy, incapability to handle complex queries and high time consumption persist. Initially, a preprocessing technique is introduced in this study, a technique that uses a median filter to remove noise to achieve improved accuracy and reliability. Then, Fourier and circularity descriptors are extract in an effective manner correspondent to the texture and affine shape adaptation features. In addition, various descriptors, such as color histogram, color moment, color autocorrelogram and color coherency vector, are extracted as the invariant color features. The multiple ant colony optimization (MACOBTC) approach is implemented with whole features to find relevant features. Finally, the relevant features are utilized for the greedy learning of deep Boltzmann machine classifier (GDBM). The proposed approach obtains effective performance and accurate results on four datasets and is analyzed with various parameters such as accuracy, precision, recall, Jaccard, Dice, and Kappa coefficients. The GDBM provides a 25% increase in accuracy compared with existing techniques, such as the a priori classification algorithm.

show abstract

Gaussian-binary restricted Boltzmann machines for modeling natural image statistics

Cited by 31 publications

References 28 publications

Deterministic and Generalized Framework for Unsupervised Learning with Restricted Boltzmann Machines

Deterministic and Generalized Framework for Unsupervised Learning with Restricted Boltzmann Machines

Size and Location Diagnosis of Rolling Bearing Faults: An Approach of Kernel Principal Component Analysis and Deep Belief Network

Greedy Learning of Deep Boltzmann Machine (GDBM)’s Variance and Search Algorithm for Efficient Image Retrieval

Contact Info

Product

Resources

About