scholarly journals Sampling the Variational Posterior with Local Refinement

Entropy ◽  
2021 ◽  
Vol 23 (11) ◽  
pp. 1475
Author(s):  
Marton Havasi ◽  
Jasper Snoek ◽  
Dustin Tran ◽  
Jonathan Gordon ◽  
José Miguel Hernández-Lobato
Keyword(s):  
Probabilistic Models ◽  
Initial Approximation ◽  
Variational Inference ◽  
Variational Approximation ◽  
Bandit Problem ◽  
Posterior Sampling ◽  
Novel Method ◽  
Model Training ◽  
Inference Methods

Variational inference is an optimization-based method for approximating the posterior distribution of the parameters in Bayesian probabilistic models. A key challenge of variational inference is to approximate the posterior with a distribution that is computationally tractable yet sufficiently expressive. We propose a novel method for generating samples from a highly flexible variational approximation. The method starts with a coarse initial approximation and generates samples by refining it in selected, local regions. This allows the samples to capture dependencies and multi-modality in the posterior, even when these are absent from the initial approximation. We demonstrate theoretically that our method always improves the quality of the approximation (as measured by the evidence lower bound). In experiments, our method consistently outperforms recent variational inference methods in terms of log-likelihood and ELBO across three example tasks: the Eight-Schools example (an inference task in a hierarchical model), training a ResNet-20 (Bayesian inference in a large neural network), and the Mushroom task (posterior sampling in a contextual bandit problem).

scholarly journals Variational Probabilistic Inference and the QMR-DT Network

1999 ◽  
Vol 10 ◽  
pp. 291-322 ◽  
Author(s):  
T. S. Jaakkola ◽  
M. I. Jordan
Keyword(s):  
Large Scale ◽  
Probabilistic Models ◽  
Graphical Model ◽  
Expert Knowledge ◽  
Probabilistic Inference ◽  
Variational Approximation ◽  
Large Set ◽  
Stochastic Sampling ◽  
Small Set ◽  
Inference Methods

We describe a variational approximation method for efficient inference in large-scale probabilistic models. Variational methods are deterministic procedures that provide approximations to marginal and conditional probabilities of interest. They provide alternatives to approximate inference methods based on stochastic sampling or search. We describe a variational approach to the problem of diagnostic inference in the `Quick Medical Reference' (QMR) network. The QMR network is a large-scale probabilistic graphical model built on statistical and expert knowledge. Exact probabilistic inference is infeasible in this model for all but a small set of cases. We evaluate our variational inference algorithm on a large set of diagnostic test cases, comparing the algorithm to a state-of-the-art stochastic sampling method.

Management of Economics and State "Bottom"

2020 ◽  
Vol 17 (6) ◽  
pp. 76-91
Author(s):  
E. D. Solozhentsev
Keyword(s):  
Quality Of Life ◽  
Artificial Intelligence ◽  
Probabilistic Models ◽  
Human Life ◽  
Special Software ◽  
Human Quality ◽  
Relationship Of ◽  
The Relationship

The scientific problem of economics “Managing the quality of human life” is formulated on the basis of artificial intelligence, algebra of logic and logical-probabilistic calculus. Managing the quality of human life is represented by managing the processes of his treatment, training and decision making. Events in these processes and the corresponding logical variables relate to the behavior of a person, other persons and infrastructure. The processes of the quality of human life are modeled, analyzed and managed with the participation of the person himself. Scenarios and structural, logical and probabilistic models of managing the quality of human life are given. Special software for quality management is described. The relationship of human quality of life and the digital economy is examined. We consider the role of public opinion in the management of the “bottom” based on the synthesis of many studies on the management of the economics and the state. The bottom management is also feedback from the top management.

scholarly journals AI-based localization and classification of skin disease with erythema

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ha Min Son ◽  
Wooho Jeon ◽  
Jinhyun Kim ◽  
Chan Yeong Heo ◽  
Hye Jin Yoon ◽  
...  
Keyword(s):  
Neural Network ◽  
Skin Diseases ◽  
Classification Model ◽  
Screening Tests ◽  
Sensitivity Score ◽  
Common Skin ◽  
Novel Method ◽  
Improved Performance ◽  
High Level

AbstractAlthough computer-aided diagnosis (CAD) is used to improve the quality of diagnosis in various medical fields such as mammography and colonography, it is not used in dermatology, where noninvasive screening tests are performed only with the naked eye, and avoidable inaccuracies may exist. This study shows that CAD may also be a viable option in dermatology by presenting a novel method to sequentially combine accurate segmentation and classification models. Given an image of the skin, we decompose the image to normalize and extract high-level features. Using a neural network-based segmentation model to create a segmented map of the image, we then cluster sections of abnormal skin and pass this information to a classification model. We classify each cluster into different common skin diseases using another neural network model. Our segmentation model achieves better performance compared to previous studies, and also achieves a near-perfect sensitivity score in unfavorable conditions. Our classification model is more accurate than a baseline model trained without segmentation, while also being able to classify multiple diseases within a single image. This improved performance may be sufficient to use CAD in the field of dermatology.

scholarly journals A novel p-harmonic descent approach applied to fluid dynamic shape optimization

2021 ◽  
Author(s):  
Peter Marvin Müller ◽  
Niklas Kühl ◽  
Martin Siebenborn ◽  
Klaus Deckelnick ◽  
Michael Hinze ◽  
...  
Keyword(s):  
Shape Optimization ◽  
Large Deformations ◽  
Fluid Dynamic ◽  
Shape Optimisation ◽  
Shape Features ◽  
Floating Bodies ◽  
Novel Method ◽  
Sharp Corners ◽  
Dynamic Shape

AbstractWe introduce a novel method for the implementation of shape optimization for non-parameterized shapes in fluid dynamics applications, where we propose to use the shape derivative to determine deformation fields with the help of the $$p-$$ p - Laplacian for $$p > 2$$ p > 2 . This approach is closely related to the computation of steepest descent directions of the shape functional in the $$W^{1,\infty }-$$ W 1 , ∞ - topology and refers to the recent publication Deckelnick et al. (A novel $$W^{1,\infty}$$ W 1 , ∞ approach to shape optimisation with Lipschitz domains, 2021), where this idea is proposed. Our approach is demonstrated for shape optimization related to drag-minimal free floating bodies. The method is validated against existing approaches with respect to convergence of the optimization algorithm, the obtained shape, and regarding the quality of the computational grid after large deformations. Our numerical results strongly indicate that shape optimization related to the $$W^{1,\infty }$$ W 1 , ∞ -topology—though numerically more demanding—seems to be superior over the classical approaches invoking Hilbert space methods, concerning the convergence, the obtained shapes and the mesh quality after large deformations, in particular when the optimal shape features sharp corners.

scholarly journals ART-UP: A Novel Method for Generating Scanning-Robust Aesthetic QR Codes

2021 ◽  
Vol 17 (1) ◽  
pp. 1-23
Author(s):  
Mingliang Xu ◽  
Qingfeng Li ◽  
Jianwei Niu ◽  
Hao Su ◽  
Xiting Liu ◽  
...  
Keyword(s):  
State Of The Art ◽  
Visual Quality ◽  
Qr Code ◽  
Quick Response ◽  
Estimation Model ◽  
Qr Codes ◽  
Excellent Performance ◽  
Novel Method ◽  
Coarse To Fine

Quick response (QR) codes are usually scanned in different environments, so they must be robust to variations in illumination, scale, coverage, and camera angles. Aesthetic QR codes improve the visual quality, but subtle changes in their appearance may cause scanning failure. In this article, a new method to generate scanning-robust aesthetic QR codes is proposed, which is based on a module-based scanning probability estimation model that can effectively balance the tradeoff between visual quality and scanning robustness. Our method locally adjusts the luminance of each module by estimating the probability of successful sampling. The approach adopts the hierarchical, coarse-to-fine strategy to enhance the visual quality of aesthetic QR codes, which sequentially generate the following three codes: a binary aesthetic QR code, a grayscale aesthetic QR code, and the final color aesthetic QR code. Our approach also can be used to create QR codes with different visual styles by adjusting some initialization parameters. User surveys and decoding experiments were adopted for evaluating our method compared with state-of-the-art algorithms, which indicates that the proposed approach has excellent performance in terms of both visual quality and scanning robustness.

scholarly journals Suspended Sediment Modeling Using a Heuristic Regression Method Hybridized with Kmeans Clustering

2021 ◽  
Vol 13 (9) ◽  
pp. 4648
Author(s):  
Rana Muhammad Adnan ◽  
Kulwinder Singh Parmar ◽  
Salim Heddam ◽  
Shamsuddin Shahid ◽  
Ozgur Kisi
Keyword(s):  
Clustering Algorithm ◽  
Suspended Sediments ◽  
Ecological Impacts ◽  
Accurate Estimation ◽  
Data Sets ◽  
The Novel ◽  
Neuro Fuzzy ◽  
Adaptive Regression ◽  
Novel Method ◽  
Model Training

The accurate estimation of suspended sediments (SSs) carries significance in determining the volume of dam storage, river carrying capacity, pollution susceptibility, soil erosion potential, aquatic ecological impacts, and the design and operation of hydraulic structures. The presented study proposes a new method for accurately estimating daily SSs using antecedent discharge and sediment information. The novel method is developed by hybridizing the multivariate adaptive regression spline (MARS) and the Kmeans clustering algorithm (MARS–KM). The proposed method’s efficacy is established by comparing its performance with the adaptive neuro-fuzzy system (ANFIS), MARS, and M5 tree (M5Tree) models in predicting SSs at two stations situated on the Yangtze River of China, according to the three assessment measurements, RMSE, MAE, and NSE. Two modeling scenarios are employed; data are divided into 50–50% for model training and testing in the first scenario, and the training and test data sets are swapped in the second scenario. In Guangyuan Station, the MARS–KM showed a performance improvement compared to ANFIS, MARS, and M5Tree methods in term of RMSE by 39%, 30%, and 18% in the first scenario and by 24%, 22%, and 8% in the second scenario, respectively, while the improvement in RMSE of ANFIS, MARS, and M5Tree was 34%, 26%, and 27% in the first scenario and 7%, 16%, and 6% in the second scenario, respectively, at Beibei Station. Additionally, the MARS–KM models provided much more satisfactory estimates using only discharge values as inputs.

scholarly journals AB0050 A NOVEL METHOD FOR ISOLATION OF EXOSOMES FROM SYNOVIAL FLUID

2021 ◽  
Vol 80 (Suppl 1) ◽  
pp. 1057.2-1057
Author(s):  
Y. Liu ◽  
Y. Huang ◽  
Q. Huang ◽  
S. Sun ◽  
Z. Ji ◽  
...  
Keyword(s):  
Synovial Fluid ◽  
Western Blot ◽  
Biological Fluid ◽  
High Sensitivity ◽  
Protein Distribution ◽  
Sds Page ◽  
Close Relationship ◽  
Novel Method ◽  
Low Levels

Background:Exosomes in synovial fluid (SF) has a close relationship with the pathogenesis of rheumatiod arthritis. As a complex biological fluid, SF presents challenges for exosomes isolation using standard methods, such as ExoquickTM kit and ultracentrifugation.Objectives:The study aims to compared the quality of exosomes separated by ExoquickTM kit (TM), ExoquickTM kit+ExoquickTC kit (TM-TC), ultracentrifugation (UC) and TM-TC+UC(TM-TC-UC) from SF.Methods:Exosomes was separated by TM, TM-TC, UC and TM-TC-UC respectively. The size and concentrations of exosomes were detected by high sensitivity flow cytometry for nanoparticle analysis. Total protein and RNA were extracted from exosomes. SDS-PAGE was used to detect the protein distribution of exosomes. Western blot was used to examine the level of albumin and exosomes marker (TSG101 and CD81).Results:There was no statistic difference in the diameters of exosomes separated by the four methods. The concentrations of exosomes in TM, TM-TC, TM-TC-UC and UC were (5.65±0.93), (3.02±1.19), (1.67±0.25) and (4.61±0.73) *109Particles/mL. The protein concentrations of exosomes separated by the four methods were consistent with the concentrations of exosomes. SDS-PAGE showed that the protein distribution of exosomes separated by the four methods were different. Low levels of albumin were detected in TM-TC and TM-TC-UC, while high levels of albumin in TM and UC. Total RNA concentrations from exosomes in TM-TC was higher than other groups.Conclusion:TM-TC can be used to obtain higher quality exosomes from SF for the study of exosome-enriched components.References:[1]Helwa I, et al, A Comparative Study of Serum Exosome Isolation Using Differential Ultracentrifugation and Three Commercial Reagents. PloS one, 2017. 12(1): p. e0170628-e0170628.Figure 1.A: SDS-PAGE showed the protein distribution of exosomes; B: the detection of albumin, TSG101 and CD81 by western blot.Disclosure of Interests:None declared

scholarly journals Using Sentinel-2 Images to Estimate Topography, Tidal-Stage Lags and Exposure Periods over Large Intertidal Areas

2021 ◽  
Vol 13 (2) ◽  
pp. 320
Author(s):  
José P. Granadeiro ◽  
João Belo ◽  
Mohamed Henriques ◽  
João Catalão ◽  
Teresa Catry
Keyword(s):  
Large Scale ◽  
Exposure Period ◽  
Intertidal Area ◽  
Digital Elevation ◽  
Geographical Bias ◽  
Novel Method ◽  
Tidal Stage ◽  
Sentinel 2

Intertidal areas provide key ecosystem services but are declining worldwide. Digital elevation models (DEMs) are important tools to monitor the evolution of such areas. In this study, we aim at (i) estimating the intertidal topography based on an established pixel-wise algorithm, from Sentinel-2 MultiSpectral Instrument scenes, (ii) implementing a set of procedures to improve the quality of such estimation, and (iii) estimating the exposure period of the intertidal area of the Bijagós Archipelago, Guinea-Bissau. We first propose a four-parameter logistic regression to estimate intertidal topography. Afterwards, we develop a novel method to estimate tide-stage lags in the area covered by a Sentinel-2 scene to correct for geographical bias in topographic estimation resulting from differences in water height within each image. Our method searches for the minimum differences in height estimates obtained from rising and ebbing tides separately, enabling the estimation of cotidal lines. Tidal-stage differences estimated closely matched those published by official authorities. We re-estimated pixel heights from which we produced a model of intertidal exposure period. We obtained a high correlation between predicted and in-situ measurements of exposure period. We highlight the importance of remote sensing to deliver large-scale intertidal DEM and tide-stage data, with relevance for coastal safety, ecology and biodiversity conservation.

Soft Reduction of a Cast Ingot on the Incomplete Crystallization Stage

2013 ◽  
Vol 762 ◽  
pp. 261-265 ◽  
Author(s):  
Tanya I. Cherkashina ◽  
Igor Mazur ◽  
Sergey A. Aksenov
Keyword(s):  
Metal Forming ◽  
Physical Simulation ◽  
Fluid Layer ◽  
Liquid Core ◽  
Soft Reduction ◽  
Deformation Processes ◽  
Novel Method ◽  
Full Scale Tests ◽  
Crystallization Stage

Numerical and physical simulation on model samples can provide data for various aspects of metal forming, without resorting to time-consuming and costly full-scale tests. This paper presents examples of modeling of the deformation of a slab with a liquid core. The use of soft reduction can enhance the homogeneity of the structure, which improves the quality of cast billets. Mathematical modeling is described here where the fluid layer is taken into account by the influence of boundary conditions in the crust in the form of ferrostatic pressure, which allows calculation of the intensity of deformation, total deformation and strain. It also provides a novel method for studying the process of soft reduction. It is based on a physical model of the slab consisting of a closed solid shell made of a calibrated lead shot and the Wood's alloy. To simulate the liquid molten metal, the interior of the shell is filled with gelatin. This approach can be applied to further studies on deformation processes and the penetration of deformation into complex metallic systems.

A Novel Method of Detecting Measurement Uncertainty of Voltage Deviation

2013 ◽  
Vol 805-806 ◽  
pp. 688-692
Author(s):  
Xin Fang ◽  
Xue Liang Huang ◽  
Yan Zhu
Keyword(s):  
Measurement Uncertainty ◽  
Power Quality ◽  
National Standards ◽  
Measurement Time ◽  
Time Interval ◽  
Basic Measurement ◽  
Voltage Deviation ◽  
Novel Method ◽  
Simulation Results

Nowadays, there are various devices to detect the power quality of AC grid, where uncertainty of voltage deviation is an important parameter to investigate the power quality. National standards specify several sinusoidal waveforms to detect it, usually implemented into the detecting devices. But these waveforms are not enough and a novel method of detecting measurement uncertainty of voltage deviation is proposed in this paper. A series of detection waveforms are designed using this method. The simulation results verify that the method is available to measure uncertainty of voltage deviation more accurately. Moreover, it can be used to justify whether the basic measurement time interval of voltage deviation meets IEC standard requirements.

Sign in / Sign up

Export Citation Format

Share Document