Recurrent-DBN models dynamic relational data with interpretable latent structures.
problem Interpreting dynamic relational data with hidden structures.
method Recurrent Dirichlet Belief Network framework with hierarchical latent structures and efficient inference strategy.
result Recurrent-DBN discovers interpretable latent structures and improves link prediction.
PROFET builds DBNs from ODEs, handling uncertainty in data and models.
problem Handling uncertainty in both data and models for DBN construction.
method Automatic DBN construction from ODEs, adaptive-time particle filtering.
result PROFET automates DBN construction and inference from ODE models.
DBNs improve accuracy of biological ODE models with missing data.
problem Uncertainty in biological ODE models with missing data.
method Converted ODE models to DBNs and used Particle Filtering for parameter estimation.
result DBNs can accurately infer model variables with missing data.
DBN-WP predicts wind power with low RMSE, MAE, and SDE.
problem Wind energy forecasting for cost reduction.
method Deep Belief Network (DBN) with multiple RBM layers for feature generation and regression.
result DBN-WP achieves low RMSE, MAE, and SDE values.
Paper develops DL methods for signal demodulation in wireless comms.
problem Signal demodulation in wireless communications.
method Proposes DBN-SVM and AdaBoost demodulators using real modulated signals.
result Proposed DBN-SVM and AdaBoost demodulators outperform traditional methods.
DBNs improve VaR forecasting compared to traditional models, but SVaR forecasts are conservative.
problem Forecasting VaR and SVaR using dynamic Bayesian networks.
method DBN framework applied to S&P 500 index returns, comparing to autoregressive models and historical simulation.
result DBNs achieve comparable VaR forecasting accuracy to historical simulation models, but SVaR forecasts remain conservative.
A new adversarial DBN framework for deep learning.
problem Training deep belief networks (DBNs) efficiently and with scalability.
method Replacing generator in GANs with DBN and developing a parallelizable training algorithm.
result Framework can be applied to general DBNs without backpropagation.
DBN improves sepsis mortality risk prediction in ICU patients.
problem Early sepsis detection in ICU patients with infection.
method Data-driven, semantically enhanced dynamic Bayesian network.
result DBN AUROC 0.91, outperforming other scoring tools.
Deep Belief Networks (DBN) have been successfully applied on popular machine learning tasks. Specifically, when applied on hand-written digit recognition, DBNs have achieved approximate accuracy rates of 98.8%. In an effort to optimize the data representation achieved by the DBN and maximize their descriptive power, re…
New approach to learning DBNs for more efficient model parameters.
problem Estimating model parameters for DBNs in a noisy environment.
method Covariance Matrix Adaptation Evolution Strategy (CMA-ES) for optimization.
result Parameters estimated in terms of efficiency, not distributional fit.
DBN whitens activations instead of just scaling them, improving deep model training.
problem Training deep models efficiently and accurately.
method Decorrelated Batch Normalization (DBN) whitens activations using PCA or ZCA, addressing stochastic axis swapping.
result DBN improves deep model performance on various datasets.
DBNs improve ES and SES estimation for market risk, but tail behavior remains challenging.
problem Optimizing ES and SES estimation for market risk in banking.
method Extended DBNs for 10-day ES and SES estimation using S&P 500 index.
result DBNs perform comparably to historical simulation but struggle with tail behavior.
NTS-NOTEARS learns DBNs from time-series data with prior knowledge.
problem Learning dynamic Bayesian networks from time-series data with nonlinear and lagged relationships.
method Uses 1D CNNs to model DBNs, incorporating prior knowledge as constraints.
result Achieves state-of-the-art DAG structure quality compared to parametric and nonparametric methods.
Research uses DBN to estimate PE ratios for better investment decisions.
problem Lack of formalized methods for estimating fundamental PE ratios.
method Dynamic Bayesian Network (DBN) methodology for estimating PE ratios.
result Trading strategy based on inferred PE ratios outperforms benchmarks.
We study the mixtures of factorizing probability distributions represented as visible marginal distributions in stochastic layered networks. We take the perspective of kernel transitions of distributions, which gives a unified picture of distributed representations arising from Deep Belief Networks (DBN) and other netw…
DBNs predict cryptocurrency price directions by uncovering causal relationships.
problem Predicting cryptocurrency price movements due to volatility and external factors.
method Dynamic Bayesian Networks (DBN) approach to identify causal relationships among features.
result DBN significantly outperforms baseline models in predicting cryptocurrency prices.
Proposes ECS-DBN for cost-sensitive deep belief network in imbalanced classification.
problem Imbalanced data classification with unequal misclassification costs.
method ECS-DBN uses adaptive differential evolution to optimize misclassification costs based on training data.
result ECS-DBN consistently outperforms state-of-the-art methods on benchmark and real-world datasets.
A new method uses ABC-SMC to infer hybrid models in bioprocesses with limited data.
problem Inference of hybrid models in bioprocesses with limited real data and high uncertainties.
method Approximate Bayesian Computation with Sequential Monte Carlo (ABC-SMC) and linear Gaussian dynamic Bayesian network (LG-DBN) for posterior distribution approximation.
result The method accelerates hybrid model inference and supports process monitoring and robust control.
Deep Belief Network predicts lncRNA-disease associations with high accuracy.
problem Accurately identifying lncRNA-disease associations to understand lncRNA functionality and disease mechanism.
method Proposes a DBN-based model using heterogeneous networks and DBN for feature learning.
result Obtained AUC of 0.96 and AUPR of 0.967 on standard dataset.
Deep learning methods have shown great promise in many practical applications, ranging from speech recognition, visual object recognition, to text processing. However, most of the current deep learning methods suffer from scalability problems for large-scale applications, forcing researchers or users to focus on small-…
A new method for CT-DCEGs simplifies inference for asymmetric processes.
problem Inference in asymmetric state space problems with continuous time evolution.
method An extension of CEG propagation for CT-DCEGs, employing junction tree inference.
result CT-DCEGs are preferred over DBNs and continuous time BNs for asymmetric processes.
Adaptive learning method improves classification in time series data analysis.
problem Improving classification capability in time series data analysis.
method Embedding adaptive learning method into recurrent temporal DBN.
result Higher classification capability than conventional methods.
A new DBN model predicts inventory levels in retail, accounting for lost items.
problem Stock freezing due to lost, stolen, or broken items.
method Dynamic Bayesian Network (DBN) with EM algorithm to estimate sales and loss distributions.
result The DBN model accurately predicts inventory levels, improving upon traditional methods.
Improved exploration in factored average-reward MDPs reduces regret.
problem Minimizing regret in unknown Factored Markov Decision Processes (FMDPs).
method DBN-UCRL strategy, inspired by UCRL2, uses Bernstein-type confidence sets for individual elements of the transition function.
result Achieves a regret bound with a leading term strictly improving over existing bounds.
Recently, the deep-belief-networks (DBN) based voice activity detection (VAD) has been proposed. It is powerful in fusing the advantages of multiple features, and achieves the state-of-the-art performance. However, the deep layers of the DBN-based VAD do not show an apparent superiority to the shallower layers. In this…
Stable topological summary captures evolving dependency structure in dynamic Bayesian networks.
problem Missing larger-scale patterns in evolving dependency structures in dynamic Bayesian networks.
method Topological approach using Dynamic Bayesian Graphs and persistent homology.
result Stable topological summary (barcodes) captures evolving dependency structure in DBNs.
Applying traditional collaborative filtering to digital publishing is challenging because user data is very sparse due to the high volume of documents relative to the number of users. Content based approaches, on the other hand, is attractive because textual content is often very informative. In this paper we describe …
Restricted Boltzmann Machines (RBMs) are one of the fundamental building blocks of deep learning. Approximate maximum likelihood training of RBMs typically necessitates sampling from these models. In many training scenarios, computationally efficient Gibbs sampling procedures are crippled by poor mixing. In this work w…
DeepSign generates malware signatures with 98.6% accuracy.
problem Detecting new malware variants using conventional methods.
method Deep Belief Network (DBN) with denoising autoencoders.
result 98.6% classification accuracy on malware variants.
Dealing with uncertainty in Bayesian Network structures using maximum a posteriori (MAP) estimation or Bayesian Model Averaging (BMA) is often intractable due to the superexponential number of possible directed, acyclic graphs. When the prior is decomposable, two classes of graphs where efficient learning can take plac…
Continuous time Bayesian networks (CTBNs) describe structured stochastic processes with finitely many states that evolve over continuous time. A CTBN is a directed (possibly cyclic) dependency graph over a set of variables, each of which represents a finite state continuous time Markov process whose transition model is…
We improve recently published results about resources of Restricted Boltzmann Machines (RBM) and Deep Belief Networks (DBN) required to make them Universal Approximators. We show that any distribution p on the set of binary vectors of length n can be arbitrarily well approximated by an RBM with k-1 hidden units, where …
Paper tackles invariance of demodulation in shallow water acoustic communications.
problem Frequency-selective signal distortion (Doppler effect) in shallow water environments.
method Developed ML-based demodulation methods using DBN-NN and DBN-CNN.
result Demonstrated invariance of the proposed method to Doppler effect with 2dB error margin.
Generative model gradients enhance MS/MS peptide identification.
problem Improving peptide identification from MS/MS spectra.
method Leverage log-likelihood gradients of generative models in a kernel-based classifier.
result Fisher kernel outperforms other methods on MS/MS datasets.
DCMAP optimizes clustering in Bayesian Networks with dependent costs.
problem Optimal clustering in Bayesian Networks with cost dependency.
method DCMAP algorithm that iteratively finds near-optimal cluster mappings.
result DCMAP finds all least cost cluster mappings optimally with minimal iterations.
We apply the spike-and-slab Restricted Boltzmann Machine (ssRBM) to texture modeling. The ssRBM with tiled-convolution weight sharing (TssRBM) achieves or surpasses the state-of-the-art on texture synthesis and inpainting by parametric models. We also develop a novel RBM model with a spike-and-slab visible layer and bi…
Paper explores ML demodulation for VLC, presenting three methods and testing accuracy.
problem Improving demodulation accuracy in VLC systems.
method Three ML demodulation methods: CNN, DBN, AdaBoost.
result AdaBoost achieves the best performance among the three methods.
Improved classification using deep belief networks with modified loss functions.
problem Enhancing classification accuracy through unsupervised and supervised learning phases.
method Developed supervised models based on deep belief networks, modified loss functions, and introduced weight bounds.
result Proposed models outperform the two-phase training approach in computational studies.
Markov random fields (MRFs) are difficult to evaluate as generative models because computing the test log-probabilities requires the intractable partition function. Annealed importance sampling (AIS) is widely used to estimate MRF partition functions, and often yields quite accurate results. However, AIS is prone to ov…
SNRA combines power-efficient probabilistic and deterministic computing for deep belief networks.
problem Efficiently training and evaluating deep belief networks with low power consumption.
method Developed a spintronic neuromorphic reconfigurable array (SNRA) for in-circuit training and evaluation of deep belief networks (DBNs). Used probabilistic spin logic devices and a four-state finite state machine for unsupervised training.
result SNRA achieves more than 80% reduction in combined dynamic and static power dissipation compared to SRAM-based configurable fabrics.
This paper presents the Speech Technology Center (STC) systems submitted to Automatic Speaker Verification Spoofing and Countermeasures (ASVspoof) Challenge 2015. In this work we investigate different acoustic feature spaces to determine reliable and robust countermeasures against spoofing attacks. In addition to the c…
This paper provides a tutorial on Boltzmann Machines and Deep Belief Networks.
problem Understanding and applying Boltzmann Machines and Deep Belief Networks.
method Explains the structures, conditional distributions, Gibbs sampling, training methods, and deep belief networks of RBMs.
result Comprehensive overview of RBMs and DBNs, useful in various fields.
DSPNs generalize SPNs for sequence data, inheriting tractable inference.
problem Inference on sequence data is often intractable.
method Dynamic Sum Product Networks (DSPNs) with a template network repeated for varying lengths.
result DSPNs inherit linear inference complexity from SPNs, unlike DBNs which are exponential.
Proposes a hierarchical model for learning discrete Bayesian networks with shrinkage.
problem Learning discrete Bayesian networks with high-order interactions and cell probabilities.
method Hierarchical Dirichlet shrinkage model with Metropolis-adjusted Langevin algorithm for sampling.
result Efficiently learns graph structure and selects between DAGs from sparse count data.
Proposes GM Score to evaluate GANs considering diversity, disentanglement, and discriminability.
problem Evaluation of GANs for sample quality and diversity.
method Integrates various factors including intra-class and inter-class diversity, disentanglement, and discriminability metrics.
result Demonstrates improved evaluation of GANs on MNIST dataset.
DeepBalance uses DBN ensembles to improve minority class prediction in imbalanced datasets.
problem Class imbalance in financial fraud detection and network intrusion analysis.
method Random DBN ensembles trained with balanced bootstraps and random feature selection.
result DeepBalance outperforms baseline resampling methods in AUC and sensitivity metrics.
This paper reviews the history and development of deep learning models.
problem Understanding the evolution and development of deep learning models.
method Review of historical models and their evolutionary paths.
result Summarizes the development and evolution of deep learning models.
This review examines DL models for financial forecasting.
problem Lack of comprehensive reviews on DL for financial forecasting.
method Categorized studies by forecasting area and DL model type.
result DL models outperform traditional ML methods.