Filters








47,539 Hits in 4.0 sec

More Buildings Make More Generalizable Models—Benchmarking Prediction Methods on Open Electrical Meter Data

Clayton Miller
2019 Machine Learning and Knowledge Extraction  
Prediction is a common machine learning (ML) technique used on building energy consumption data.  ...  This example implementation shows that there is no one size-fits-all modeling solution and that various types of temporal behavior are difficult to capture using machine learning.  ...  for several machine learning studies.  ... 
doi:10.3390/make1030056 fatcat:cmoa7xfknve4jbyg3hhbnkqvwa

Towards automated kernel selection in machine learning systems: A SYCL case study [article]

John Lawson
2020 arXiv   pre-print
Traditional kernel auto-tuning has limited impact in this case; a more general selection of kernels is required for libraries to accelerate machine learning research.  ...  This approach is good for deploying machine learning models, where the network topology is constant, but machine learning research often involves changing network topologies and hyperparameters.  ...  Over 80% of the variance is accounted for in the 4 main components, 90% is accounted for in 8 components, and 95% in 15.  ... 
arXiv:2003.06795v1 fatcat:6kq36lxjvbfpnn26x3xmh5wp44

A critical analysis of variants of the AUC

Stijn Vanderlooy, Eyke Hüllermeier
2008 Machine Learning  
Machine Learning 72(3), 247-262 (September 2008) This is an extended abstract of an article published in the Machine Learning Journal [1].  ...  For this reason, three variants of the AUC metric that take the score differences into account have recently been proposed, along with first experimental results.  ...  For this reason, three variants of the AUC metric that take the score differences into account have recently been proposed, along with first experimental results.  ... 
doi:10.1007/s10994-008-5070-x fatcat:2oazlhyprvct7ke2evvp4w2kma

An Assessment of Qualitative Performance of Machine Learning Architectures: Modular Feedback Networks

Mo Chen, T. Gautama, D.P. Mandic
2008 IEEE Transactions on Neural Networks  
A framework for the assessment of qualitative performance of machine learning architectures is proposed.  ...  delay vector variance (DVV) method for phase space signal characterization.  ...  Usually, a small number of principal components is sufficient to account for most of the structure in the data.  ... 
doi:10.1109/tnn.2007.902728 pmid:18269949 fatcat:2ennrs72vvbt3ap5dngnk2q5oy

Performance prediction based on inherent program similarity

Kenneth Hoste, Aashish Phansalkar, Lieven Eeckhout, Andy Georges, Lizy K. John, Koen De Bosschere
2006 Proceedings of the 15th international conference on Parallel architectures and compilation techniques - PACT '06  
space in which the relative distance is a measure for the relative performance differences.  ...  Our framework estimates per-benchmark machine ranks with a 0.89 average and a 0.80 worst case rank correlation coefficient.  ...  Acknowledgements This research is supported in part by Ghent University, the Institute for the Promotion of Innovation by Science and Technology in Flanders (IWT), the Fund for Scientific Research -Flanders  ... 
doi:10.1145/1152154.1152174 dblp:conf/IEEEpact/HostePEGJB06 fatcat:rdit4xeq7fdxdflfczyve44nuy

General Guide to Applying Machine Learning to Computer Architecture

2018 Supercomputing Frontiers and Innovations  
learning in computer architecture.  ...  The resurgence of machine learning since the late 1990s has been enabled by significant advances in computing performance and the growth of big data.  ...  Another method for accounting for benchmark idiosyncrasies could be using an equal number of samples from each of the workloads in the train set during the learning phase.  ... 
doi:10.14529/jsfi180106 fatcat:jnpuo2fonnbbhprktcj4hy3iui

Benchmarking and Scalability of Machine Learning Methods for Photometric Redshift Estimation [article]

Ben Henghes, Connor Pettitt, Jeyan Thiyagalingam, Tony Hey, Ofer Lahav
2021 arXiv   pre-print
Here, we introduce a benchmark designed to analyse the performance and scalability of different supervised machine learning methods for photometric redshift estimation.  ...  In creating novel methods to produce redshift estimations, there has been a shift towards using machine learning techniques.  ...  DATA AVAILABILITY The data used in this paper came entirely from the Sloan Digital Sky Survey data release 12 (SDSS-DR12), and is openly available from: https://www.sdss.org/dr12/.  ... 
arXiv:2104.01875v1 fatcat:w4jmrt45sbdppluv2amwsjndby

A Methodology for Analyzing Commercial Processor Performance Numbers

Kenneth Hoste, Lieven Eeckhout
2009 Computer  
mance speedup numbers for all machines and benchmarks in the SPEC CPU2000 benchmark suite.  ...  The S matrix consists of 1,123 rows-there are 1,123 machines in our dataset-and 26 columns-there are 26 benchmarks in the SPEC CPU2000 benchmark suite.  ...  Acknowledgments Kenneth Hoste is supported through a PhD student fellowship from the Institute for the Promotion of Innovation by Science and Technology in Flanders, Belgium.  ... 
doi:10.1109/mc.2009.307 fatcat:jhe54thkt5gjlbggkshz47kpry

Park: An Open Platform for Learning-Augmented Computer Systems

Hongzi Mao, Parimarjan Negi, Akshay Narayan, Hanrui Wang, Jiacheng Yang, Haonan Wang, Ryan Marcus, Ravichandra Addanki, Mehrdad Khani Shirkoohi, Songtao He, Vikram Nathan, Frank Cangialosi (+5 others)
2019 Neural Information Processing Systems  
We present Park, a platform for researchers to experiment with Reinforcement Learning (RL) for computer systems.  ...  Using RL for improving the performance of systems has a lot of potential, but is also in many ways very different from, for example, using RL for games.  ...  This work was funded in part by the NSF grants CNS-1751009, CNS-1617702, a Google Faculty Research Award, an AWS Machine Learning Research Award, a Cisco Research Center Award, an Alfred P.  ... 
dblp:conf/nips/MaoNN0YWMASHNCV19 fatcat:ns664s6rjnhe7ioiz56z57vkai

Can Machine Learning-Based Portfolios Outperform Traditional Risk-Based Portfolios? The Need to Account for Covariance Misspecification

Prayut Jain, Shashi Jain
2019 Risks  
Next, we study under an appropriate covariance forecast model whether the machine learning based HRP outperforms the traditional risk-based portfolios.  ...  We find that when the covariance estimates are crude, inverse volatility weighted portfolios are more robust, followed by the machine learning-based portfolios.  ...  The results show that for both, machine learning based HRP variants and the traditional risk-based portfolios, DCC GARCH can be considered as the benchmark model in majority of the universes.  ... 
doi:10.3390/risks7030074 fatcat:m7q663bu25gm5ddz7fgbmpn3cm

Optimizing Ensemble Weights and Hyperparameters of Machine Learning Models for Regression Problems [article]

Mohsen Shahhosseini, Guiping Hu, Hieu Pham
2020 arXiv   pre-print
In stacking with the weighted average, ensembles are created from weighted averages of multiple base learners.  ...  While bagging and boosting focus more on reducing variance and bias, respectively, stacking approaches target both by finding the optimal way to combine base learners.  ...  Four machine learning algorithms with minimal pre-processing tasks were designed for each data set separately and the designed algorithm is applied to them.  ... 
arXiv:1908.05287v6 fatcat:byfi3zpksfgglmm4hnhxdizsua

Dynamic Feature Selection for Machine-Learning Based Concurrency Regulation in STM

Diego Rughetti, Pierangelo Di Sanzo, Bruno Ciciani, Francesco Quaglia
2014 2014 22nd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing  
In this paper we explore machine-learning based approaches for dynamically selecting the well suited amount of concurrent threads in applications relying on Software Transactional Memory (STM).  ...  We also present a fully fledged implementation of our proposal within the TinySTM open source framework, and provide the results of an experimental study relying in the STAMP benchmark suite, which show  ...  On the other hand, one drawback of machine learning is related to the need for constantly monitoring the set of selected input features to be exploited by the machine learner.  ... 
doi:10.1109/pdp.2014.24 dblp:conf/pdp/RughettiSCQ14 fatcat:oe75grgoeje6dog5kp2n6tdh3m

Enactment Ranking of Supervised Algorithms Dependence of Data Splitting Algorithms: A Case Study of Real Datasets

Hina Tabassum
2020 Zenodo  
In line with the expectations, every supervised learning classifier demonstrated different capability for different data splitting algorithms and no way to calculate overall ranking of techniques was directly  ...  of learning classifier algorithms.  ...  Training Datasets A subset of original datasets used for estimating and learning the parameter of the required machine learning algorithms.  ... 
doi:10.5281/zenodo.3793845 fatcat:rz2ucvs5pfeb7fgkykdxmv7jtm

A Prediction Model Optimization Critiques through Centroid Clustering by Reducing the Sample Size, Integrating Statistical and Machine Learning Techniques for Wheat Productivity

Muhammad Islam, Farrukh Shehzad, Mehdi Rahimi
2022 Scientifica  
Machine learning algorithms are rapidly deploying and have made manifold breakthroughs in various fields.  ...  The optimization of algorithms got abundant attention of researchers being a core component for deploying the machine learning model (MLM) abled to learn the parameters in significant ways for the given  ...  Muhammad Omar, Assistant Professor, Department of Computer Science, the Islamia University of Bahawalpur, Pakistan, for their appreciable directions regarding implementations of machine learning techniques  ... 
doi:10.1155/2022/7271293 pmid:35310811 pmcid:PMC8933067 fatcat:bmiofvb5obcdtj7lnnmi3kc2ju

A machine learning ensemble to predict treatment outcomes following an Internet intervention for depression

Rahel Pearson, Derek Pisner, Björn Meyer, Jason Shumake, Christopher G. Beevers
2018 Psychological Medicine  
Machine learning ensembles may be a promising statistical approach for identifying the cumulative contribution of many weak predictors to psychosocial depression treatment response.  ...  Model performance was evaluated using predictive R2 $\lpar R_{{\rm pred}}^2\rpar\comma $ the expected variance explained in a new sample, estimated by 10 repetitions of 10-fold cross-validation.ResultsAn  ...  Foundation, a 501(c)(3) not-for-profit philanthropic foundation that supports mental health programs in Austin, TX, USA.  ... 
doi:10.1017/s003329171800315x pmid:30392475 pmcid:PMC6763538 fatcat:qyo7ybuoubcpfjiesa2p2ejnty
« Previous Showing results 1 — 15 out of 47,539 results