Filters








13,706 Hits in 3.8 sec

BigDataGrapes D4.3 - Models and Tools for Predictive Analytics over Extremely Large Datasets

Nicola Tonellotto, Vinicius Monteiro de Lira, Franco Maria Nardini, Raffaele Perego, Cristina Muntean, Ida Mele, Salvatore Trani
2018 Zenodo  
Layers of the BDG architecture contributed in Deliverable 4.1 "Methods and Tools for Scalable Distributed Processing".  ...  The BDG software stack employs efficient and fault-tolerant tools for distributed processing, aimed at providing scalability and reliability for the target applications.  ...  Layers of the BDG architecture contributed in Deliverable 4.1 "Methods and Tools for Scalable Distributed Processing" D4.3 | Models and Tools for Predictive Analytics over Extremely Large Datasets 6  ... 
doi:10.5281/zenodo.1481800 fatcat:rlqwgvajzre6pfxuiiclmk2r34

A Hadoop-Based Method to Predict Potential Effective Drug Combination

Yifan Sun, Yi Xiong, Qian Xu, Dongqing Wei
2014 BioMed Research International  
However, exhaustive screening of all possible drug combinations is extremely time-consuming and impractical.  ...  The experimental results suggest that our Hadoop-based model achieves much higher efficiency in the big data processing steps with satisfactory performance.  ...  Extension to a Scalable Mining Process.  ... 
doi:10.1155/2014/196858 pmid:25147789 pmcid:PMC4134802 fatcat:ng2aqwb37jg43bw5jsykx5tfja

Predicting optimal operation of MC-3DSBC multidimensional scalable video coding using subjective quality measurement

Yong Wang, Tian-Tsong Ng, Mihaela van der Schaar, Shih-Fu Chang, Sethuraman Panchanathan, Bhaskaran Vasudev
2004 Visual Communications and Image Processing 2004  
For this purpose we firstly explore the behavior of SNR-Spatial-Temporal scalability using Motion Compensated (MC) SBC systems.  ...  Based on the system behavior, we propose an efficient method for the optimal selection of scalability operator through contentbased prediction.  ...  For the online processing routing, the content features of the incoming video will be used by the classification function.  ... 
doi:10.1117/12.527413 dblp:conf/vcip/WangNSC04 fatcat:ikuxigtxsjaq7kxdjiqttxivpm

BigDataGrapes D4.3 - Models and Tools for Predictive Analytics over Extremely Large Datasets

Nicola Tonellotto, Vinicius Monteiro de Lira, Franco Maria Nardini, Raffaele Perego, Cristina Muntean, Ida Mele, Salvatore Trani, Matteo Ceneta
2019 Zenodo  
Layers of the BDG architecture contributed in Deliverable 4.1: "Methods and Tools for Scalable Distributed Processing".  ...  The BDG software stack employs efficient and fault-tolerant tools for distributed processing, aimed at providing scalability and reliability for the target applications.  ...  Layers of the BDG architecture contributed in Deliverable 4.1: "Methods and Tools for Scalable Distributed Processing".  ... 
doi:10.5281/zenodo.2641952 fatcat:n6ag6qt4gzg6tmnytqs2f7op4u

Fully Scalable Gaussian Processes using Subspace Inducing Inputs [article]

Aristeidis Panos, Petros Dellaportas, Michalis K. Titsias
2018 arXiv   pre-print
We introduce fully scalable Gaussian processes, an implementation scheme that tackles the problem of treating a high number of training instances together with high dimensional input data.  ...  Our illustrative applications are based on challenging extreme multi-label classification problems with the extra burden of the very large number of class labels.  ...  We call the resulting implementation strategy as fully scalable Gaussian processes because we achieve scalability in both N and D.  ... 
arXiv:1807.02537v2 fatcat:vd35plevurb4nccraxk546riim

Extreme Outcomes, Connectivity, and Power Laws: Towards an Econophysics of Organization [chapter]

Max Boisot, Bill McKelvey
2013 Knowledge, Organization, and Management  
Organization science needs to find ways of studying extremes more rigorously.  ...  Managers are often required to respond in adaptive ways to the threats and opportunities presented by rare, extreme outcomes.  ...  How does "Paretian" scalable abduction differ from "Gaussian" abduction? By exploiting the scale-free character of extreme outcomes.  ... 
doi:10.1093/acprof:oso/9780199669165.003.0004 fatcat:wckr2yulfvagbij4kgsmq4nq4m

Scalable Variational Gaussian Process Classification [article]

James Hensman, Alex Matthews, Zoubin Ghahramani
2014 arXiv   pre-print
Gaussian process classification is a popular method with a number of appealing properties.  ...  Importantly, the variational formulation can be exploited to allow classification in problems with millions of data points, as we demonstrate in experiments.  ...  arXiv:1411.2005v1 [stat.ML] 7 Nov 2014Gaussian Process Classification Gaussian process priors provide rich nonparametric models of functions.  ... 
arXiv:1411.2005v1 fatcat:iledvquffndcbh6sdbun7uo2wi

Deep Kernel Learning [article]

Andrew Gordon Wilson, Zhiting Hu, Ruslan Salakhutdinov, Eric P. Xing
2015 arXiv   pre-print
We jointly learn the properties of these kernels through the marginal likelihood of a Gaussian process.  ...  On a large and diverse collection of applications, including a dataset with 2 million examples, we show improved performance over scalable Gaussian processes with flexible kernel learning models, and stand-alone  ...  processes or other kernel machines for scalable learning. dimensions.  ... 
arXiv:1511.02222v1 fatcat:guzfr767yfaupjvorzo2rycmzy

Supervised Learning for Optimal Power Flow as a Real-Time Proxy [article]

Raphael Canyasse, Gal Dalal, Shie Mannor
2016 arXiv   pre-print
The motivation for quick calculation of OPF cost outcomes stems from the growing need of algorithmic-based long-term and medium-term planning methodologies in power networks.  ...  Integrated in a multiple time-horizon coordination framework, we refer to this approximation module as a proxy for predicting short-term decision outcomes without the need of actual simulation and optimization  ...  We show that for the test-cases inspected, extremely high accuracy for both feasibility classification and cost regression are obtainable.  ... 
arXiv:1612.06623v1 fatcat:pdinrey35rdgxmxws7ile42aku

Distributed Learning over Massive XML Documents in ELM Feature Space

Xin Bi, Xiangguo Zhao, Guoren Wang, Zhen Zhang, Shuang Chen
2015 Mathematical Problems in Engineering  
Learning Machine for mining tasks of classification or clustering.  ...  Extensive experiments are conducted on massive XML documents datasets to verify the effectiveness and efficiency for both classification and clustering applications.  ...  H; (4) Calculate = H † T; Algorithm 3: Extreme Learning Machine for classification.  ... 
doi:10.1155/2015/923097 fatcat:2qxlvlx2pfesbnsgxzsgaplaea

Scalable Partial Explainability in Neural Networks via Flexible Activation Functions [article]

Schyler C. Sun, Chen Li, Zhuangkun Wei, Antonios Tsourdos, Weisi Guo
2020 arXiv   pre-print
This is carried out by modeling the AFs as adaptive Gaussian Processes (GP), which sit within a novel scalable NN topology, based on the Kolmogorov-Arnold Superposition Theorem (KST).  ...  To demonstrate this, we perform a case study on a binary classification dataset of banknote authentication.  ...  Gaussian Process activation functions, we are able to demonstrate a new degree of interpretability.  ... 
arXiv:2006.06057v1 fatcat:s5skggzrajbhhiypgluwxzccee

A scalable end-to-end Gaussian process adapter for irregularly sampled time series classification [article]

Steven Cheng-Xian Li, Benjamin Marlin
2016 arXiv   pre-print
We present a general framework for classification of sparse and irregularly-sampled time series.  ...  To address these challenges, we propose an uncertainty-aware classification framework based on a special computational layer we refer to as the Gaussian process adapter that can connect irregularly sampled  ...  Gaussian processes for sparse and irregularly-sampled time series Our focus in this paper is on time series classification in the presence of sparse and irregular sampling.  ... 
arXiv:1606.04443v2 fatcat:3rnane45zjg4hlfufitmomkb2y

Large scale multi-label learning using Gaussian processes

Aristeidis Panos, Petros Dellaportas, Michalis K. Titsias
2021 Machine Learning  
AbstractWe introduce a Gaussian process latent factor model for multi-label classification that can capture correlations among class labels by using a small set of latent Gaussian process functions.  ...  To address computational challenges, when the number of training instances is very large, we introduce several techniques based on variational sparse Gaussian process approximations and stochastic optimization  ...  The whole process becomes somehow similar to negative sampling used in large scale classification and for learning word embeddings Mikolov et al. (2013) .  ... 
doi:10.1007/s10994-021-05952-5 fatcat:gd6fzrwagjf35b43wdl4qyrqgq

Generic Inference in Latent Gaussian Process Models [article]

Edwin V. Bonilla and Karl Krauth and Amir Dezfouli
2018 arXiv   pre-print
We develop an automated variational method for inference in models with Gaussian process (GP) priors and general likelihoods.  ...  On the large-scale experiments involving prediction of airline delays and classification of handwritten digits, we show that our method is on par with the state-of-the-art hard-coded approaches for scalable  ...  Conclusions and Discussion We have developed scalable automated variational inference for Gaussian process models (savigp), an inference method for models with Gaussian process (gp) priors, multiple outputs  ... 
arXiv:1609.00577v2 fatcat:ngpjezdvv5egheozyzc2pr3qya

Scalable neural architectures for end-to-end environmental sound classification

Francesco Paissan, Alberto Ancilotto, Alessio Brutti, Elisabetta Farella
2022 Zenodo  
In particular, our architectures achieve state-of-the-art performance on UrbanSound8K in spectrogram classification (around 77%) with extreme compression factors (99.8%) with respect to current state-of-the-art  ...  Here, urban sounds can be detected and processed by embedded devices in an Internet of Things (IoT) to identify meaningful events for municipalities or law enforcement.  ...  Such scalability features allow for extreme model compression and optimization, while decoupling parameter count and computational cost in alignment with the harware-aware scaling paradigm.  ... 
doi:10.5281/zenodo.6351853 fatcat:bolkyk54pjbc3b3ikyhwte5wyq
« Previous Showing results 1 — 15 out of 13,706 results