Improved Gaussian–Bernoulli restricted Boltzmann machine for learning discriminative representations

Zhang, Ji; Wang, Hongjun; Chu, Jielei; Li, Tianrui; Zhao, Qibin

doi:10.1016/j.knosys.2019.104911

Cited by 23 publications

(5 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Restricted Boltzmann Machine (RBM) is an undirected neural network model and has only visible layer and hidden layer. Since the pioneering work of Geoffrey Hinton in 1986 [30], RBM has been widely used in industry, such as recommendation system, document classification, information retrieval, language processing, and time series prediction [16,24,[31][32][33].…”

Section: Chaotic Restricted Boltzmann Machine (Crbm)mentioning

confidence: 99%

Image sharing based on 3D-BCNN and Blockchain Authentication

Wang,

Jia,

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

In the current trend of cloud storage and data sharing, image trading and consumption are increasingly frequent. Therefore, the protection of sensitive images and identity authentication become urgent. In this paper, an image sharing method based on 3-dimensional Boolean convolution neural network (3D-BCNN) and blockchain is proposed. Unlike traditional symmetric encryption algorithms, this paper introduces an asymmetric key cryptosystem, which allow different users to receive image with authorization without knowing the key of the data owner. The correctness authentication of the acquired image is based on blockchain, which is immutable and reliable. In pre-transmission encryption, 3D convolution matrices are designed by Chaotic Restricted Boltzmann Machine(CRBM), convolution kernel and shuffle rule are generated by novel two-parameters wide-range mapping mixed Coupled Map Lattice (TWM-CML), and each channel performs Boolean XOR convolution operation. The experimental simulation shows that the secret image has better security properties than the state-of-the-art algorithms. Furthermore, the algorithm provides an end-to-end trusted image protection system and authenticate efficiently.

show abstract

Section: Chaotic Restricted Boltzmann Machine (Crbm)mentioning

confidence: 99%

Image sharing based on 3D-BCNN and Blockchain Authentication

Wang,

Jia,

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…WARSAW, POLAND, 2023 [48]. Restricted Boltzmann Machines are one very rudimentary implementation of such EBMs and have been studied in the literature, even though their capabilities in computer vision are very limited, as they model the data distribution, which is rarely feasible for images of a real-world size [49], [50]. Similar as with RBMs, self-organizing maps [51] are a popular choice, especially in life sciences and genetics, but have come unfashionable due to their poor scalability.…”

Section: H Preliminary Workmentioning

confidence: 99%

Can Unlabelled Data Improve AI Applications? A Comparative Study on Self-Supervised Learning in Computer Vision.

Bauer,

Augenstein

2023

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Artificial Intelligence (AI) represents a highly investigated area of study at present and has already become an indispensable component within an extensive range of business models and applications. One major downside of current supervised AI approaches lies in the need of numerous annotated data points to train the models. Self-supervised learning (SSL) circumvents the need for annotation, by creating supervision signals such as labels from the data itself, rather than requiring experts for this task. Current approaches mainly include the use of generative methods such as autoencoders and joint embedding architectures to fulfil this task. Recent works present comparable results to supervised learning in downstream scenarios such as classification after SSL-pretraining. To achieve this, typically modifications are required to suit the approach for the exact downstream task. Yet, current review works haven't paid too much attention to the practical implications of using SSL. Thus, we investigated and implemented popular SSL approaches, suitable for downstream tasks such as classification, from an initial collection of more than 400 papers. We evaluate a selection of these approaches under real-world dataset conditions, and in direct comparison to the supervised learning scenario. We discuss SSL's potential to take up with supervised learning, as well as the influence of the right training methods. Furthermore, we also introduce future directions for SSL research, as well as current limitations in real-world applications.

show abstract

“…Paper [116] proposed an improved RBM with a new regularization term to automatically generate features that are suitable for predicting remaining useful life. In [117], the authors proposed a Teager-Kaiser energy operator to estimate the envelope of the instantaneous signal and extract the statistical feature of the data, and then propose Gaussian-Bernoulli RBM (GRBM) to construct a DBN for real-valued classification [118].…”

Section: Deep Belief Network Based Fault Diagnosismentioning

confidence: 99%

Deep Learning-Based Fault Diagnosis of Photovoltaic Systems: A Comprehensive Review and Enhancement Prospects

Mansouri¹,

Trabelsi

Nounou

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Photovoltaic (PV) systems are subject to failures during their operation due to the aging effects and external/environmental conditions. These faults may affect the different system components such as PV modules, connection lines, converters/inverters, which can lead to a decrease in the efficiency, performance, and further system collapse. Thus, a key factor to be taken into consideration in high-efficiency grid-connected PV systems is the fault detection and diagnosis (FDD). The performance of the FDD method depends mainly on the quality of the extracted features including real-time changes, phase changes, trend changes, and faulty modes. Thus, the data representation learning is the core stage of intelligent FDD techniques. Recently, due to the enhancement of computing capabilities, the increase of the big data use, and the development of effective algorithms, the deep learning (DL) tool has witnessed a great success in data science. Therefore, this paper proposes an extensive review on deep learning based FDD methods for PV systems. After a brief description of the DL-based strategies, techniques for diagnosing PV systems proposed in recent literature are overviewed and analyzed to point out their differences, advantages and limits. Future research directions towards the improvement of the performance of the DL-based FDD techniques are also discussed. This review paper aims to systematically present the development of DLbased FDD for PV systems and provide guidelines for future research in the field.

show abstract

Improved Gaussian–Bernoulli restricted Boltzmann machine for learning discriminative representations

Cited by 23 publications

References 37 publications

Image sharing based on 3D-BCNN and Blockchain Authentication

Image sharing based on 3D-BCNN and Blockchain Authentication

Can Unlabelled Data Improve AI Applications? A Comparative Study on Self-Supervised Learning in Computer Vision.

Deep Learning-Based Fault Diagnosis of Photovoltaic Systems: A Comprehensive Review and Enhancement Prospects

Contact Info

Product

Resources

About