Restricted Boltzmann Machine Network Research Articles

Quantum state tomography of multi-qubit systems — a comparative study

Multi-qubit state tomography is a key problem in quantum information technology, which has been studied extensively. In this work, we focus on multi-qubit state tomography based on neural network estimators and typical conventional estimation approaches. For multi-qubit pure states, fully connected neural networks and restricted Boltzmann machine networks are designed, respectively, to carry out state tomography of 2-qubit (low-dimensional) systems and 5-qubit (high-dimensional) systems. Comparisons are made with maximum likelihood estimation and least squares estimation, where performance indicators are selected as reconstruction accuracy, time cost and the number of parameters. Simulation results indicate that intelligent approaches have significant advantages over conventional approaches for state tomography of low-dimensional systems; for high-dimensional systems, however, the conventional approach is still dominant when the measurement is complete, while the restricted Boltzmann machine network can achieve higher reconstruction accuracy when the measurement is incomplete.

Retinal optical coherence tomography image analysis by a restricted Boltzmann machine.

Optical coherence tomography (OCT) is an emerging imaging technique for ophthalmic disease diagnosis. Two major problems in OCT image analysis are image enhancement and image segmentation. Deep learning methods have achieved excellent performance in image analysis. However, most of the deep learning-based image analysis models are supervised learning-based approaches and need a high volume of training data (e.g., reference clean images for image enhancement and accurate annotated images for segmentation). Moreover, acquiring reference clean images for OCT image enhancement and accurate annotation of the high volume of OCT images for segmentation is hard. So, it is difficult to extend these deep learning methods to the OCT image analysis. We propose an unsupervised learning-based approach for OCT image enhancement and abnormality segmentation, where the model can be trained without reference images. The image is reconstructed by Restricted Boltzmann Machine (RBM) by defining a target function and minimizing it. For OCT image enhancement, each image is independently learned by the RBM network and is eventually reconstructed. In the reconstruction phase, we use the ReLu function instead of the Sigmoid function. Reconstruction of images given by the RBM network leads to improved image contrast in comparison to other competitive methods in terms of contrast to noise ratio (CNR). For anomaly detection, hyper-reflective foci (HF) as one of the first signs in retinal OCTs of patients with diabetic macular edema (DME) are identified based on image reconstruction by RBM and post-processing by removing the HFs candidates outside the area between the first and the last retinal layers. Our anomaly detection method achieves a high ability to detect abnormalities.

Interactive 3D reconstruction method of fuzzy static images in social media

Abstract Because the traditional social media fuzzy static image interactive three-dimensional (3D) reconstruction method has the problem of poor reconstruction completeness and long reconstruction time, the social media fuzzy static image interactive 3D reconstruction method is proposed. For preprocessing the fuzzy static image of social media, the Harris corner detection method is used to extract the feature points of the preprocessed fuzzy static image of social media. According to the extraction results, the parameter estimation algorithm of contrast divergence is used to learn the restricted Boltzmann machine (RBM) network model, and the RBM network model is divided into input, output, and hidden layers. By combining the RBM-based joint dictionary learning method and a sparse representation model, an interactive 3D reconstruction of fuzzy static images in social media is achieved. Experimental results based on the CAD software show that the proposed method has a reconstruction completeness of above 95% and the reconstruction time is less than 15 s, improving the completeness and efficiency of the reconstruction, effectively reconstructing the fuzzy static images in social media, and increasing the sense of reality of social media images.

Design of On-line Simulation System for Signal Control of Urban Intersections Based on Visual Sensing Technology

Intersection area is the area with the most serious conflicts and accidents in the whole urban traffic system. Therefore, it is of great significance to combine modern computer technology, sensing technology and communication technology to intelligently control intersections, improve the efficiency of traffic signal control and reduce the delay time in conflict areas. Starting with video detection and using deep learning in the detection module, a video detection mechanism based on restricted Boltzmann machine network is proposed. Based on C # programming language, the intersection traffic signal simulation module is designed through COM interface provided by traffic simulation software VISSIM, which realizes road network import, parameter setting, signal timing change, simulation operation and simulation result output. Numerical experiments show that fuzzy control method with self-correcting factor is superior to timing control method and classical fuzzy control method in average delay time of vehicles.

Dropout Deep Belief Network Based Chinese Ancient Ceramic Non-Destructive Identification.

A non-destructive identification method was developed here based on dropout deep belief network in multi-spectral data of ancient ceramic. A fractional differential algorithm was proposed to enhance the spectral details by making use of the difference between the first and second-order differential pre-process spectral data. An unsupervised multi-layer restricted Boltzmann machine (RBM) was employed to extract some high-level features during pre-training. Some weight and bias values trained by RBM were used to initialize a back propagation (BP) neural network. The RBM deep belief network was fine-tuned by the BP neural network to promote the initiative performance of network training, which helped to overcome local optimal limitation of the network due to the random initializing weight parameter. The dropout strategy has been put forward into the RBM network to solve the over-fitting of small sample spectral data. The experimental results show that the proposed method has excellent recognition performance of the ceramics by comparisons with some other ones.

Short-sighted deep learning.

A theory explaining how deep learning works is yet to be developed. Previous work suggests that deep learning performs a coarse graining, similar in spirit to the renormalization group (RG). This idea has been explored in the setting of a local (nearest-neighbor interactions) Ising spin lattice. We extend the discussion to the setting of a long-range spin lattice. Markov-chain Monte Carlo (MCMC) simulations determine both the critical temperature and scaling dimensions of the system. The model is used to train both a single restricted Boltzmann machine (RBM) network, as well as a stacked RBM network. Following earlier Ising model studies, the trained weights of a single-layer RBM network define a flow of lattice models. In contrast to results for nearest-neighbor Ising, the RBM flow for the long-ranged model does not converge to the correct values for the spin and energy scaling dimension. Further, correlation functions between visible and hidden nodes exhibit key differences between the stacked RBM and RG flows. The stacked RBM flow appears to move toward low temperatures, whereas the RG flow moves toward high temperature. This again differs from results obtained for nearest-neighbor Ising.

Generating the conformational properties of a polymer by the restricted Boltzmann machine.

In polymer theory, computer-generated polymer configurations, by either Monte Carlo simulations or molecular dynamics simulations, help us to establish the fundamental understanding of the conformational properties of polymers. Here, we introduce a different method, exploiting the properties of a machine-learning algorithm, the restricted Boltzmann machine network, to generate independent polymer configurations for self-avoiding walks (SAWs), for studying the conformational properties of polymers. We show that with adequate training data and network size, this method can capture the underlying polymer physics simply from learning the statistics in the training data without explicit information on the physical model itself. We critically examine how the trained Boltzmann machine can generate independent configurations that are not in the original training data set of SAWs.

On the Representational Power of Restricted Boltzmann Machines for Symmetric Functions and Boolean Functions.

Restricted Boltzmann machines (RBMs) are used to build deep-belief networks that are widely thought to be one of the first effective deep learning neural networks. This paper studies the ability of RBMs to represent distributions over {0,1}n via softplus/hardplus RBM networks. It is shown that any distribution whose density depends on the number of 1's in their input can be approximated with arbitrarily high accuracy by an RBM of size 2n+1 , which improves the result of a previous study by reducing the size from n2 to 2n+1 . A theorem for representing partially symmetric Boolean functions by softplus RBM networks is established. Accordingly, the representational power of RBMs for distributions whose mass represents the Boolean functions is investigated in comparison with that of threshold circuits and polynomial threshold functions. It is shown that a distribution over {0,1}n whose mass represents a Boolean function can be computed with a given margin δ by an RBM of size and parameters bounded by polynomials in n , if and only if it can be computed by a depth-2 threshold circuit with size and parameters bounded by polynomials in n .

Feature expansion by a continuous restricted Boltzmann machine for near-infrared spectrometric calibration

A modified algorithm for training a restricted Boltzmann machine (RBM) has been devised and demonstrated for improving the results for partial least squares (PLS) calibration of wheat and meat by near-infrared (NIR) spectroscopy. In all cases, the PLS calibrations improved by using the abstract features generated from the RBM so long as the nonlinear mapping increased the dimensionality. The evaluations were validated using bootstrapped Latin partitions (BLPs) with 5 bootstraps and 3-Latin partitions which proved useful because of the statistical learning and random initial conditions of the RBM networks. By using a noise decay parameter, initial large amounts of noise could be used and the benefits of simulated annealing achieved as the noise level is slowly decreased. This paper demonstrates for the first time that using abstract features and enlarging the spectral data can improve the calibration results and exemplifies the Copiosity Principle. Two NIR reference datasets were evaluated. The first set of wheat spectra was calibrated for protein concentration and the second set of meat spectra was calibrated for moisture, fat, and protein concentration. The RBM feature extraction improved the linearity of the models and reduced embedded noise. The RBM also can help eliminate some difficult spectral preprocessing stages such as variable alignment and feature selection. RBMs benefit from derivative preprocessing of the NIR spectra or other preprocessing that enhances the differences among the spectra.

A new item-based deep network structure using a restricted Boltzmann machine for collaborative filtering

The collaborative filtering (CF) technique has been widely used recently in recommendation systems. It needs historical data to give predictions. However, the data sparsity problem still exists. We propose a new item-based restricted Boltzmann machine (RBM) approach for CF and use the deep multilayer RBM network structure, which alleviates the data sparsity problem and has excellent ability to extract features. Each item is treated as a single RBM, and different items share the same weights and biases. The parameters are learned layer by layer in the deep network. The batch gradient descent algorithm with minibatch is used to increase the convergence speed. The new feature vector discovered by the multilayer RBM network structure is very effective in predicting a rating and achieves a better result. Experimental results on the data set of MovieLens show that the item-based multilayer RBM approach achieves the best performance, with a mean absolute error of 0.6424 and a root-mean-square error of 0.7843.

Tolerance of intrinsic device variation in fuzzy restricted Boltzmann machine network based on memristive nano-synapses

Inspired by the architecture and principle of the human brain, neuromorphic computing has attracted enormous research interest due to its potential for massively parallel and energy-efficient computing, where nanoscale memristors are considered as perfect building blocks for hardware neural networks, serving as compact, analog synapses. However, the inherent variation in memristors has been regarded as a major obstacle to their practical application in neuromorphic computing. Here, for the first time, we demonstrate that this long-standing issue can be addressed by introducing fuzziness into the neural networks. We found that the cycle-to-cycle and device-to-device conductance variations in the on and off states of Pt/TaOx/Ta memristors statistically follow Gaussian distributions, and using an experimentally verified compact synapse model based on the electrical characteristics of Pt/TaOx/Ta devices, a fuzzy restricted Boltzmann machine (FRBM) network was constructed where all the weight states were fuzzified to accommodate device stochasticity. The FRBM network has shown significantly improved tolerance to device variation, as confirmed by increased accuracy in the benchmark test of MNIST handwritten digit classifications. This study thus provides a new route towards highly robust neuromorphic computing, even if the computing elements can be stochastic and inhomogeneous.

A Multilayer Improved RBM Network Based Image Compression Method in Wireless Sensor Networks

The processing capacity and power of nodes in a Wireless Sensor Network (WSN) are limited. And most image compression algorithms in WSN are subject to random image content changes or have low image qualities after the images are decoded. Therefore, an image compression method based on multilayer Restricted Boltzmann Machine (RBM) network is proposed in this paper. The alternative iteration algorithm is also applied in RBM to optimize the training process. The proposed image compression method is compared with a region of interest (ROI) compression method in simulations. Under the same compression ratio, the qualities of reconstructed images are better than that of ROI. When the number of hidden units in top RBM layer is 8, the peak signal-to-noise ratio (PSNR) of the multilayer RBM network compression method is 74.2141, and it is much higher than that of ROI which is 60.2093. The multilayer RBM based image compression method has better compression performance and can effectively reduce the energy consumption during image transmission in WSN.

Deep Learning in Drug Discovery.

Artificial neural networks had their first heyday in molecular informatics and drug discovery approximately two decades ago. Currently, we are witnessing renewed interest in adapting advanced neural network architectures for pharmaceutical research by borrowing from the field of "deep learning". Compared with some of the other life sciences, their application in drug discovery is still limited. Here, we provide an overview of this emerging field of molecular informatics, present the basic concepts of prominent deep learning methods and offer motivation to explore these techniques for their usefulness in computer-assisted drug discovery and design. We specifically emphasize deep neural networks, restricted Boltzmann machine networks and convolutional networks.

An Algorithm of Quantum Restricted Boltzmann Machine Network Based on Quantum Gates and Its Application

We present an algorithm of quantum restricted Boltzmann machine network based on quantum gates. The algorithm is used to initialize the procedure that adjusts the qubit and weights. After adjusting, the network forms an unsupervised generative model that gives better classification performance than other discriminative models. In addition, we show how the algorithm can be constructed with quantum circuit for quantum computer.