scholarly journals Large scale tensor regression using kernels and variational inference

2021 ◽  
Author(s):  
Robert Hu ◽  
Geoff K. Nicholls ◽  
Dino Sejdinovic
Keyword(s):  
Large Scale ◽  
Side Information ◽  
Variational Inference ◽  
Superior Performance ◽  
Tensor Factorization ◽  
Latent Factors ◽  
Uncertainty Estimates ◽  
Novel Method ◽  
Prediction And Forecasting ◽  
Large Scale Tensor

AbstractWe outline an inherent flaw of tensor factorization models when latent factors are expressed as a function of side information and propose a novel method to mitigate this. We coin our methodology kernel fried tensor (KFT) and present it as a large-scale prediction and forecasting tool for high dimensional data. Our results show superior performance against LightGBM and Field aware factorization machines (FFM), two algorithms with proven track records, widely used in large-scale prediction. We also develop a variational inference framework for KFT which enables associating the predictions and forecasts with calibrated uncertainty estimates on several datasets.

scholarly journals Deeply Fusing Reviews and Contents for Cold Start Users in Cross-Domain Recommendation Systems

2019 ◽  
Vol 33 ◽  
pp. 94-101 ◽  
Author(s):  
Wenjing Fu ◽  
Zhaohui Peng ◽  
Senzhang Wang ◽  
Yang Xu ◽  
Jin Li
Keyword(s):  
Semantic Information ◽  
Side Information ◽  
Recommendation Systems ◽  
Cold Start ◽  
Superior Performance ◽  
Fusion Model ◽  
Target Domain ◽  
Latent Factors ◽  
Data Sparsity ◽  
Cross Domain

As one promising way to solve the challenging issues of data sparsity and cold start in recommender systems, crossdomain recommendation has gained increasing research interest recently. Cross-domain recommendation aims to improve the recommendation performance by means of transferring explicit or implicit feedback from the auxiliary domain to the target domain. Although the side information of review texts and item contents has been proven to be useful in recommendation, most existing works only use one kind of side information and cannot deeply fuse this side information with ratings. In this paper, we propose a Review and Content based Deep Fusion Model named RC-DFM for crossdomain recommendation. We first extend Stacked Denoising Autoencoders (SDAE) to effectively fuse review texts and item contents with the rating matrix in both auxiliary and target domains. Through this way, the learned latent factors of users and items in both domains preserve more semantic information for recommendation. Then we utilize a multi-layer perceptron to transfer user latent factors between the two domains to address the data sparsity and cold start issues. Experimental results on real datasets demonstrate the superior performance of RC-DFM compared with state-of-the-art recommendation methods.Deeply Fusing Reviews and Contents for Cold Start Users in Cross-Domain Recommendation Systems

Tensor Factorization and Clustering for the Feature Extraction Based on Tucker3 with Updating Core

2011 ◽  
Vol 308-310 ◽  
pp. 2517-2522 ◽  
Author(s):  
Hai Jun Wang ◽  
Fei Yun Xu ◽  
Fei Wang
Keyword(s):  
Feature Extraction ◽  
Parallel Computing ◽  
Large Scale ◽  
Tensor Factorization ◽  
Parallel Mode ◽  
Large Scale Tensor

Aiming at the problems of Tucker3 to large-scale tensor when applied to feature extraction, a new factorization based on Tucker3 is proposed to extract feature from the tensors. First, the large-scale tensor is divided into multiple sub-tensors so as to conveniently compute cores of sub-tensors in parallel mode with Matlab Parallel Computing Toolbox; Then, the cores of each sub-tensor are updated for reducing deviation in calculating and the similar characteristics of sub-tensors are clustered to obtain the features. Experiment results show that this methods is able to extract features rapidly and efficiently.

Enzymatic Synthesis of 15N-L-aspartic Acid Using Recombinant Aspartase from Escherichia Coli K12

2008 ◽  
Vol 59 (11) ◽  
Author(s):  
Iulia Lupan ◽  
Sergiu Chira ◽  
Maria Chiriac ◽  
Nicolae Palibroda ◽  
Octavian Popescu
Keyword(s):  
Amino Acids ◽  
Aspartic Acid ◽  
Enzymatic Synthesis ◽  
Large Scale ◽  
Recombinant Dna ◽  
Industrial Enzymes ◽  
Recombinant Dna Technology ◽  
Bacterial Fermentation ◽  
Natural Protein ◽  
Novel Method

Amino acids are obtained by bacterial fermentation, extraction from natural protein or enzymatic synthesis from specific substrates. With the introduction of recombinant DNA technology, it has become possible to apply more rational approaches to enzymatic synthesis of amino acids. Aspartase (L-aspartate ammonia-lyase) catalyzes the reversible deamination of L-aspartic acid to yield fumaric acid and ammonia. It is one of the most important industrial enzymes used to produce L-aspartic acid on a large scale. Here we described a novel method for [15N] L-aspartic synthesis from fumarate and ammonia (15NH4Cl) using a recombinant aspartase.

scholarly journals SAR Target Recognition via Meta-Learning and Amortized Variational Inference

Sensors ◽  
2020 ◽  
Vol 20 (20) ◽  
pp. 5966
Author(s):  
Ke Wang ◽  
Gong Zhang
Keyword(s):  
Target Recognition ◽  
Probability Distributions ◽  
Automatic Target Recognition ◽  
Variational Inference ◽  
Training Data ◽  
Superior Performance ◽  
Small Data ◽  
Meta Learning ◽  
Radar Automatic Target Recognition ◽  
Global Parameters

The challenge of small data has emerged in synthetic aperture radar automatic target recognition (SAR-ATR) problems. Most SAR-ATR methods are data-driven and require a lot of training data that are expensive to collect. To address this challenge, we propose a recognition model that incorporates meta-learning and amortized variational inference (AVI). Specifically, the model consists of global parameters and task-specific parameters. The global parameters, trained by meta-learning, construct a common feature extractor shared between all recognition tasks. The task-specific parameters, modeled by probability distributions, can adapt to new tasks with a small amount of training data. To reduce the computation and storage cost, the task-specific parameters are inferred by AVI implemented with set-to-set functions. Extensive experiments were conducted on a real SAR dataset to evaluate the effectiveness of the model. The results of the proposed approach compared with those of the latest SAR-ATR methods show the superior performance of our model, especially on recognition tasks with limited data.

scholarly journals Examination of Construct Validity and Criterion-Related Validity of the German Motor Test in Egyptian Schoolchildren

2021 ◽  
Vol 18 (16) ◽  
pp. 8341
Author(s):  
Osama Abdelkarim ◽  
Julian Fritsch ◽  
Darko Jekauc ◽  
Klaus Bös
Keyword(s):  
Construct Validity ◽  
Physical Fitness ◽  
Large Scale ◽  
Body Height ◽  
Cross Sectional Study ◽  
Latent Factors ◽  
Cross Sectional ◽  
First Order ◽  
Motor Test ◽  
Health Related

Physical fitness is an indicator for children’s public health status. Therefore, the aim of this study was to examine the construct validity and the criterion-related validity of the German motor test (GMT) in Egyptian schoolchildren. A cross-sectional study was conducted with a total of 931 children aged 6 to 11 years (age: 9.1 ± 1.7 years) with 484 (52%) males and 447 (48%) females in grades one to five in Assiut city. The children’s physical fitness data were collected using GMT. GMT is designed to measure five health-related physical fitness components including speed, strength, coordination, endurance, and flexibility of children aged 6 to 18 years. The anthropometric data were collected based on three indicators: body height, body weight, and BMI. A confirmatory factor analysis was conducted with IBM SPSS AMOS 26.0 using full-information maximum likelihood. The results indicated an adequate fit (χ2 = 112.3, df = 20; p < 0.01; CFI = 0.956; RMSEA = 0.07). The χ2-statistic showed significant results, and the values for CFI and RMSEA showed a good fit. All loadings of the manifest variables on the first-order latent factors as well as loadings of the first-order latent factors on the second-order superordinate factor were significant. The results also showed strong construct validity in the components of conditioning abilities and moderate construct validity in the components of coordinative abilities. GMT proved to be a valid method and could be widely used on large-scale studies for health-related fitness monitoring in the Egyptian population.

scholarly journals Uncertainty-Aware Deep Learning-Based Cardiac Arrhythmias Classification Model of Electrocardiogram Signals

Computers ◽  
2021 ◽  
Vol 10 (6) ◽  
pp. 82
Author(s):  
Ahmad O. Aseeri
Keyword(s):  
Deep Learning ◽  
Cardiac Arrhythmias ◽  
Large Scale ◽  
Clinical Decision Making ◽  
Probabilistic Approach ◽  
Classification Model ◽  
Gating Mechanism ◽  
Uncertainty Estimates ◽  
Wide Range

Deep Learning-based methods have emerged to be one of the most effective and practical solutions in a wide range of medical problems, including the diagnosis of cardiac arrhythmias. A critical step to a precocious diagnosis in many heart dysfunctions diseases starts with the accurate detection and classification of cardiac arrhythmias, which can be achieved via electrocardiograms (ECGs). Motivated by the desire to enhance conventional clinical methods in diagnosing cardiac arrhythmias, we introduce an uncertainty-aware deep learning-based predictive model design for accurate large-scale classification of cardiac arrhythmias successfully trained and evaluated using three benchmark medical datasets. In addition, considering that the quantification of uncertainty estimates is vital for clinical decision-making, our method incorporates a probabilistic approach to capture the model’s uncertainty using a Bayesian-based approximation method without introducing additional parameters or significant changes to the network’s architecture. Although many arrhythmias classification solutions with various ECG feature engineering techniques have been reported in the literature, the introduced AI-based probabilistic-enabled method in this paper outperforms the results of existing methods in outstanding multiclass classification results that manifest F1 scores of 98.62% and 96.73% with (MIT-BIH) dataset of 20 annotations, and 99.23% and 96.94% with (INCART) dataset of eight annotations, and 97.25% and 96.73% with (BIDMC) dataset of six annotations, for the deep ensemble and probabilistic mode, respectively. We demonstrate our method’s high-performing and statistical reliability results in numerical experiments on the language modeling using the gating mechanism of Recurrent Neural Networks.

scholarly journals A Novel Method to Predict Drug-Target Interactions Based on Large-Scale Graph Representation Learning

Cancers ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 2111
Author(s):  
Bo-Wei Zhao ◽  
Zhu-Hong You ◽  
Lun Hu ◽  
Zhen-Hao Guo ◽  
Lei Wang ◽  
...  
Keyword(s):  
Drug Target ◽  
Large Scale ◽  
Computational Models ◽  
Structural Information ◽  
Characteristic Curve ◽  
Representation Learning ◽  
Graph Representation ◽  
Convolutional Network ◽  
Novel Method

Identification of drug-target interactions (DTIs) is a significant step in the drug discovery or repositioning process. Compared with the time-consuming and labor-intensive in vivo experimental methods, the computational models can provide high-quality DTI candidates in an instant. In this study, we propose a novel method called LGDTI to predict DTIs based on large-scale graph representation learning. LGDTI can capture the local and global structural information of the graph. Specifically, the first-order neighbor information of nodes can be aggregated by the graph convolutional network (GCN); on the other hand, the high-order neighbor information of nodes can be learned by the graph embedding method called DeepWalk. Finally, the two kinds of feature are fed into the random forest classifier to train and predict potential DTIs. The results show that our method obtained area under the receiver operating characteristic curve (AUROC) of 0.9455 and area under the precision-recall curve (AUPR) of 0.9491 under 5-fold cross-validation. Moreover, we compare the presented method with some existing state-of-the-art methods. These results imply that LGDTI can efficiently and robustly capture undiscovered DTIs. Moreover, the proposed model is expected to bring new inspiration and provide novel perspectives to relevant researchers.

scholarly journals A Novel Method Facilitating the Simple and Low-Cost Preparation of Human Osteochondral Slice Explants for Large-Scale Native Tissue Analysis

2021 ◽  
Vol 22 (12) ◽  
pp. 6394
Author(s):  
Jacob Spinnen ◽  
Lennard K. Shopperly ◽  
Carsten Rendenbach ◽  
Anja A. Kühl ◽  
Ufuk Sentürk ◽  
...  
Keyword(s):  
Gene Expression ◽  
Cell Viability ◽  
Large Scale ◽  
Marker Gene ◽  
Cell Swelling ◽  
Tissue Cell ◽  
Joint Research ◽  
Sample Number ◽  
Tnf Α ◽  
Novel Method

For in vitro modeling of human joints, osteochondral explants represent an acceptable compromise between conventional cell culture and animal models. However, the scarcity of native human joint tissue poses a challenge for experiments requiring high numbers of samples and makes the method rather unsuitable for toxicity analyses and dosing studies. To scale their application, we developed a novel method that allows the preparation of up to 100 explant cultures from a single human sample with a simple setup. Explants were cultured for 21 days, stimulated with TNF-α or TGF-β3, and analyzed for cell viability, gene expression and histological changes. Tissue cell viability remained stable at >90% for three weeks. Proteoglycan levels and gene expression of COL2A1, ACAN and COMP were maintained for 14 days before decreasing. TNF-α and TGF-β3 caused dose-dependent changes in cartilage marker gene expression as early as 7 days. Histologically, cultures under TNF-α stimulation showed a 32% reduction in proteoglycans, detachment of collagen fibers and cell swelling after 7 days. In conclusion, thin osteochondral slice cultures behaved analogously to conventional punch explants despite cell stress exerted during fabrication. In pharmacological testing, both the shorter diffusion distance and the lack of need for serum in the culture suggest a positive effect on sensitivity. The ease of fabrication and the scalability of the sample number make this manufacturing method a promising platform for large-scale preclinical testing in joint research.

Sign in / Sign up

Export Citation Format

Share Document