keyword
MENU ▼
Read by QxMD icon Read
search

restricted Boltzmann machine

keyword
https://www.readbyqxmd.com/read/29772725/attention-based-recurrent-temporal-restricted-boltzmann-machine-for-radar-high-resolution-range-profile-sequence-recognition
#1
Yifan Zhang, Xunzhang Gao, Xuan Peng, Jiaqi Ye, Xiang Li
The High Resolution Range Profile (HRRP) recognition has attracted great concern in the field of Radar Automatic Target Recognition (RATR). However, traditional HRRP recognition methods failed to model high dimensional sequential data efficiently and have a poor anti-noise ability. To deal with these problems, a novel stochastic neural network model named Attention-based Recurrent Temporal Restricted Boltzmann Machine (ARTRBM) is proposed in this paper. RTRBM is utilized to extract discriminative features and the attention mechanism is adopted to select major features...
May 16, 2018: Sensors
https://www.readbyqxmd.com/read/29727443/an-improved-advertising-ctr-prediction-approach-based-on-the-fuzzy-deep-neural-network
#2
Zilong Jiang, Shu Gao, Mingjiang Li
Combining a deep neural network with fuzzy theory, this paper proposes an advertising click-through rate (CTR) prediction approach based on a fuzzy deep neural network (FDNN). In this approach, fuzzy Gaussian-Bernoulli restricted Boltzmann machine (FGBRBM) is first applied to input raw data from advertising datasets. Next, fuzzy restricted Boltzmann machine (FRBM) is used to construct the fuzzy deep belief network (FDBN) with the unsupervised method layer by layer. Finally, fuzzy logistic regression (FLR) is utilized for modeling the CTR...
2018: PloS One
https://www.readbyqxmd.com/read/29570642/competitive-deep-belief-networks-for-underwater-acoustic-target-recognition
#3
Honghui Yang, Sheng Shen, Xiaohui Yao, Meiping Sheng, Chen Wang
Underwater acoustic target recognition based on ship-radiated noise belongs to the small-sample-size recognition problems. A competitive deep-belief network is proposed to learn features with more discriminative information from labeled and unlabeled samples. The proposed model consists of four stages: (1) A standard restricted Boltzmann machine is pretrained using a large number of unlabeled data to initialize its parameters; (2) the hidden units are grouped according to categories, which provides an initial clustering model for competitive learning; (3) competitive training and back-propagation algorithms are used to update the parameters to accomplish the task of clustering; (4) by applying layer-wise training and supervised fine-tuning, a deep neural network is built to obtain features...
March 23, 2018: Sensors
https://www.readbyqxmd.com/read/29562690/representation-learning-for-class-c-g-protein-coupled-receptors-classification
#4
Raúl Cruz-Barbosa, Erik-German Ramos-Pérez, Jesús Giraldo
G protein-coupled receptors (GPCRs) are integral cell membrane proteins of relevance for pharmacology. The complete tertiary structure including both extracellular and transmembrane domains has not been determined for any member of class C GPCRs. An alternative way to work on GPCR structural models is the investigation of their functionality through the analysis of their primary structure. For this, sequence representation is a key factor for the GPCRs' classification context, where usually, feature engineering is carried out...
March 19, 2018: Molecules: a Journal of Synthetic Chemistry and Natural Product Chemistry
https://www.readbyqxmd.com/read/29548112/phase-diagram-of-restricted-boltzmann-machines-and-generalized-hopfield-networks-with-arbitrary-priors
#5
Adriano Barra, Giuseppe Genovese, Peter Sollich, Daniele Tantari
Restricted Boltzmann machines are described by the Gibbs measure of a bipartite spin glass, which in turn can be seen as a generalized Hopfield network. This equivalence allows us to characterize the state of these systems in terms of their retrieval capabilities, both at low and high load, of pure states. We study the paramagnetic-spin glass and the spin glass-retrieval phase transitions, as the pattern (i.e., weight) distribution and spin (i.e., unit) priors vary smoothly from Gaussian real variables to Boolean discrete variables...
February 2018: Physical Review. E
https://www.readbyqxmd.com/read/29531065/blindfold-learning-of-an-accurate-neural-metric
#6
Christophe Gardella, Olivier Marre, Thierry Mora
The brain has no direct access to physical stimuli but only to the spiking activity evoked in sensory organs. It is unclear how the brain can learn representations of the stimuli based on those noisy, correlated responses alone. Here we show how to build an accurate distance map of responses solely from the structure of the population activity of retinal ganglion cells. We introduce the Temporal Restricted Boltzmann Machine to learn the spatiotemporal structure of the population activity and use this model to define a distance between spike trains...
March 27, 2018: Proceedings of the National Academy of Sciences of the United States of America
https://www.readbyqxmd.com/read/29522400/a-hybrid-network-for-erp-detection-and-analysis-based-on-restricted-boltzmann-machine
#7
Jingcong Li, Zhu Liang Yu, Zhenghui Gu, Wei Wu, Yuanqing Li, Lianwen Jin
Detecting and Please provide the correct one analyzing the event-related potential (ERP) remains an important problem in neuroscience. Due to the low signal-to-noise ratio and complex spatio-temporal patterns of ERP signals, conventional methods usually rely on ensemble averaging technique for reliable detection, which may obliterate subtle but important information in each trial of ERP signals. Inspired by deep learning methods, we propose a novel hybrid network termed ERP-NET. With hybrid deep structure, the proposed network is able to learn complex spatial and temporal patterns from single-trial ERP signals...
March 2018: IEEE Transactions on Neural Systems and Rehabilitation Engineering
https://www.readbyqxmd.com/read/29457314/latent-source-mining-in-fmri-via-restricted-boltzmann-machine
#8
Xintao Hu, Heng Huang, Bo Peng, Junwei Han, Nian Liu, Jinglei Lv, Lei Guo, Christine Guo, Tianming Liu
Blind source separation (BSS) is commonly used in functional magnetic resonance imaging (fMRI) data analysis. Recently, BSS models based on restricted Boltzmann machine (RBM), one of the building blocks of deep learning models, have been shown to improve brain network identification compared to conventional single matrix factorization models such as independent component analysis (ICA). These models, however, trained RBM on fMRI volumes, and are hence challenged by model complexity and limited training set...
February 18, 2018: Human Brain Mapping
https://www.readbyqxmd.com/read/29447667/feature-expansion-by-a-continuous-restricted-boltzmann-machine-for-near-infrared-spectrometric-calibration
#9
Peter de Boves Harrington
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...
June 20, 2018: Analytica Chimica Acta
https://www.readbyqxmd.com/read/29377804/an-on-chip-learning-neuromorphic-autoencoder-with-current-mode-transposable-memory-read-and-virtual-lookup-table
#10
Hwasuk Cho, Hyunwoo Son, Kihwan Seong, Byungsub Kim, Hong-June Park, Jae-Yoon Sim
This paper presents an IC implementation of on-chip learning neuromorphic autoencoder unit in a form of rate-based spiking neural network. With a current-mode signaling scheme embedded in a 500 × 500 6b SRAM-based memory, the proposed architecture achieves simultaneous processing of multiplications and accumulations. In addition, a transposable memory read for both forward and backward propagations and a virtual lookup table are also proposed to perform an unsupervised learning of restricted Boltzmann machine...
February 2018: IEEE Transactions on Biomedical Circuits and Systems
https://www.readbyqxmd.com/read/29360786/study-on-urban-heat-island-intensity-level-identification-based-on-an-improved-restricted-boltzmann-machine
#11
Yang Zhang, Ping Jiang, Hongyan Zhang, Peng Cheng
Thermal infrared remote sensing has become one of the main technology methods used for urban heat island research. When applying urban land surface temperature inversion of the thermal infrared band, problems with intensity level division arise because the method is subjective. However, this method is one of the few that performs heat island intensity level identification. This paper will build an intensity level identifier for an urban heat island, by using weak supervision and thought-based learning in an improved, restricted Boltzmann machine (RBM) model...
January 23, 2018: International Journal of Environmental Research and Public Health
https://www.readbyqxmd.com/read/29350321/sliding-to-predict-vision-based-beating-heart-motion-estimation-by-modeling-temporal-interactions
#12
Angelica I Aviles-Rivero, Samar M Alsaleh, Alicia Casals
PURPOSE: Technical advancements have been part of modern medical solutions as they promote better surgical alternatives that serve to the benefit of patients. Particularly with cardiovascular surgeries, robotic surgical systems enable surgeons to perform delicate procedures on a beating heart, avoiding the complications of cardiac arrest. This advantage comes with the price of having to deal with a dynamic target which presents technical challenges for the surgical system. In this work, we propose a solution for cardiac motion estimation...
March 2018: International Journal of Computer Assisted Radiology and Surgery
https://www.readbyqxmd.com/read/29347631/phase-transitions-in-restricted-boltzmann-machines-with-generic-priors
#13
Adriano Barra, Giuseppe Genovese, Peter Sollich, Daniele Tantari
We study generalized restricted Boltzmann machines with generic priors for units and weights, interpolating between Boolean and Gaussian variables. We present a complete analysis of the replica symmetric phase diagram of these systems, which can be regarded as generalized Hopfield models. We underline the role of the retrieval phase for both inference and learning processes and we show that retrieval is robust for a large class of weight and unit priors, beyond the standard Hopfield scenario. Furthermore, we show how the paramagnetic phase boundary is directly related to the optimal size of the training set necessary for good generalization in a teacher-student scenario of unsupervised learning...
October 2017: Physical Review. E
https://www.readbyqxmd.com/read/29289703/enhancing-interpretability-of-automatically-extracted-machine-learning-features-application-to-a-rbm-random-forest-system-on-brain-lesion-segmentation
#14
Sérgio Pereira, Raphael Meier, Richard McKinley, Roland Wiest, Victor Alves, Carlos A Silva, Mauricio Reyes
Machine learning systems are achieving better performances at the cost of becoming increasingly complex. However, because of that, they become less interpretable, which may cause some distrust by the end-user of the system. This is especially important as these systems are pervasively being introduced to critical domains, such as the medical field. Representation Learning techniques are general methods for automatic feature computation. Nevertheless, these techniques are regarded as uninterpretable "black boxes"...
February 2018: Medical Image Analysis
https://www.readbyqxmd.com/read/29060298/informative-sensor-selection-and-learning-for-prediction-of-lower-limb-kinematics-using-generative-stochastic-neural-networks
#15
Eunsuk Chong, Taejin Choi, Hyungmin Kim, Seung-Jong Kim, Yoha Hwang, Jong Min Lee
We propose a novel approach of selecting useful input sensors as well as learning a mathematical model for predicting lower limb joint kinematics. We applied a feature selection method based on the mutual information called the variational information maximization, which has been reported as the state-of-the-art work among information based feature selection methods. The main difficulty in applying the method is estimating reliable probability density of input and output data, especially when the data are high dimensional and real-valued...
July 2017: Conference Proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society
https://www.readbyqxmd.com/read/29059905/classification-of-respiratory-disturbances-in-rett-syndrome-patients-using-restricted-boltzmann-machine
#16
Heather M O'Leary, Juan Manuel Mayor, Chi-Sang Poon, Walter E Kaufmann, Mustafa Sahin
Rett syndrome (RTT) is a severe neurodevelopmental disorder that can cause pervasive wakeful respiratory disturbances that include tachypnea, breath-holding, and central apnea. Quantitative analysis of these respiratory disturbances in RTT is considered a promising outcome measure for clinical trials. Currently, machine learning methodologies have not been employed to automate the classification of RTT respiratory disturbances. In this paper, we propose using temporal, flow, and autocorrelation features taken from the respiratory inductance plethsymography chest signal...
July 2017: Conference Proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society
https://www.readbyqxmd.com/read/29020921/identify-huntington-s-disease-associated-genes-based-on-restricted-boltzmann-machine-with-rna-seq-data
#17
Xue Jiang, Han Zhang, Feng Duan, Xiongwen Quan
BACKGROUND: Predicting disease-associated genes is helpful for understanding the molecular mechanisms during the disease progression. Since the pathological mechanisms of neurodegenerative diseases are very complex, traditional statistic-based methods are not suitable for identifying key genes related to the disease development. Recent studies have shown that the computational models with deep structure can learn automatically the features of biological data, which is useful for exploring the characteristics of gene expression during the disease progression...
October 11, 2017: BMC Bioinformatics
https://www.readbyqxmd.com/read/28964083/unsupervised-modulation-filter-learning-for-noise-robust-speech-recognition
#18
Purvi Agrawal, Sriram Ganapathy
The modulation filtering approach to robust automatic speech recognition (ASR) is based on enhancing perceptually relevant regions of the modulation spectrum while suppressing the regions susceptible to noise. In this paper, a data-driven unsupervised modulation filter learning scheme is proposed using convolutional restricted Boltzmann machine. The initial filter is learned using the speech spectrogram while subsequent filters are learned using residual spectrograms. The modulation filtered spectrograms are used for ASR experiments on noisy and reverberant speech where these features provide significant improvements over other robust features...
September 2017: Journal of the Acoustical Society of America
https://www.readbyqxmd.com/read/28950614/nonequilibrium-thermodynamics-of-restricted-boltzmann-machines
#19
Domingos S P Salazar
In this work, we analyze the nonequilibrium thermodynamics of a class of neural networks known as restricted Boltzmann machines (RBMs) in the context of unsupervised learning. We show how the network is described as a discrete Markov process and how the detailed balance condition and the Maxwell-Boltzmann equilibrium distribution are sufficient conditions for a complete thermodynamics description, including nonequilibrium fluctuation theorems. Numerical simulations in a fully trained RBM are performed and the heat exchange fluctuation theorem is verified with excellent agreement to the theory...
August 2017: Physical Review. E
https://www.readbyqxmd.com/read/28939812/efficient-representation-of-quantum-many-body-states-with-deep-neural-networks
#20
Xun Gao, Lu-Ming Duan
Part of the challenge for quantum many-body problems comes from the difficulty of representing large-scale quantum states, which in general requires an exponentially large number of parameters. Neural networks provide a powerful tool to represent quantum many-body states. An important open question is what characterizes the representational power of deep and shallow neural networks, which is of fundamental interest due to the popularity of deep learning methods. Here, we give a proof that, assuming a widely believed computational complexity conjecture, a deep neural network can efficiently represent most physical states, including the ground states of many-body Hamiltonians and states generated by quantum dynamics, while a shallow network representation with a restricted Boltzmann machine cannot efficiently represent some of those states...
September 22, 2017: Nature Communications
keyword
keyword
74746
1
2
Fetch more papers »
Fetching more papers... Fetching...
Read by QxMD. Sign in or create an account to discover new knowledge that matter to you.
Remove bar
Read by QxMD icon Read
×

Search Tips

Use Boolean operators: AND/OR

diabetic AND foot
diabetes OR diabetic

Exclude a word using the 'minus' sign

Virchow -triad

Use Parentheses

water AND (cup OR glass)

Add an asterisk (*) at end of a word to include word stems

Neuro* will search for Neurology, Neuroscientist, Neurological, and so on

Use quotes to search for an exact phrase

"primary prevention of cancer"
(heart or cardiac or cardio*) AND arrest -"American Heart Association"