Filters








38 Hits in 9.8 sec

Introduction to Machine Learning for the Sciences [article]

Titus Neupert, Mark H Fischer, Eliska Greplova, Kenny Choo, Michael Denner
2021 arXiv   pre-print
The notes start with an exposition of machine learning methods without neural networks, such as principle component analysis, t-SNE, and linear regression.  ...  This is an introductory machine learning course specifically developed with STEM students in mind. We discuss supervised, unsupervised, and reinforcement learning.  ...  Neural networks, in contrast, are a non-linear method for supervised classification and regression tasks.  ... 
arXiv:2102.04883v1 fatcat:pynwxolq6rarbnxxcnbm7yqt3e

A comprehensive survey on machine learning for networking: evolution, applications and research opportunities

Raouf Boutaba, Mohammad A. Salahuddin, Noura Limam, Sara Ayoubi, Nashid Shahriar, Felipe Estrada-Solano, Oscar M. Caicedo
2018 Journal of Internet Services and Applications  
Therefore, this is a timely contribution of the implications of ML for networking, that is pushing the barriers of autonomic network operation and management.  ...  There are various surveys on ML for specific areas in networking or for specific network technologies.  ...  Acknowledgments We thank the anonymous reviewers for their insightful comments and suggestions that helped us improve the quality of the paper.  ... 
doi:10.1186/s13174-018-0087-2 fatcat:jvwpewceevev3n4keoswqlcacu

Faster Maxflow via Improved Dynamic Spectral Vertex Sparsifiers [article]

Jan van den Brand, Yu Gao, Arun Jambulapati, Yin Tat Lee, Yang P. Liu, Richard Peng, Aaron Sidford
2021 arXiv   pre-print
Combining these pieces with modifications to prior robust interior point frameworks gives an algorithm that on graphs with m edges computes a mincost flow with edge costs and capacities in [1, U] in time  ...  In prior and independent work, [Axiotis-Mądry-Vladu FOCS 2021] also obtained an improved algorithm for sparse mincost flows on capacitated graphs.  ...  Liu, Thatchaphol Saranurak, Aaron Sidford, Zhao Song, and Di Wang. Minimum cost flows, mdps, and ℓ1 -regression in nearly linear time for dense instances.  ... 
arXiv:2112.00722v1 fatcat:v5fv24yzpbdrzlkeso4ofz5haq

SeReMAS: Self-Resilient Mobile Autonomous Systems Through Predictive Edge Computing [article]

Davide Callegaro and Marco Levorato and Francesco Restuccia
2021 arXiv   pre-print
However, in practical applications, erratic patterns in channel quality, network load, and edge server load can interrupt the task flow execution, which necessarily leads to severe disruption of the system's  ...  We extensively evaluate SeReMAS by considering an application where one drone offloads high-resolution images for real-time analysis to three edge servers on the ground.  ...  We use feature importance methods such as Logistic Regression, Support Vector Machines and Random Forest as implemented in [15] and selected Logistic Regression with L1 regularizer due to the bias that  ... 
arXiv:2105.15105v2 fatcat:yol3jdjyr5g6bbciftvpblj7ca

Modelling the transition to a low-carbon energy supply [article]

Alexander Kell
2021 arXiv   pre-print
This is due to many long-term uncertainties, such as electricity, fuel and generation costs, human behaviour and the size of electricity demand.  ...  In contrast to other works, this thesis looks at both the long-term and short-term impact that different behaviours have on the electricity market by using these state-of-the-art methods.  ...  Other methods for fitting linear regressions are by minimising a penalised version of the leastsquares cost function, such as in ridge and lasso regression [83, 231] .  ... 
arXiv:2111.00987v1 fatcat:cltjuirij5fvfhxeoonaxqrs4m

The Vessel Schedule Recovery Problem (VSRP) – A MIP model for handling disruptions in liner shipping

Berit D. Brouer, Jakob Dirksen, David Pisinger, Christian E.M. Plum, Bo Vaaben
2013 European Journal of Operational Research  
The proposed model incorporates a matching algorithm between the supply and demand, finding the most adequate option, considering multiple objectives, as minimum travel time for passengers and balance  ...  This talk provides an overview of major modeling and computational challenges in the development of deterministic and stochastic linear/nonlinear mixedinteger optimization models for planning and scheduling  ...  , Moscow Institute of Physics and Tehnology, Russian Federation, atygaevdr@gmail.com, Vadim Mottl In this paper, we review time-varying linear regression, which is the essence of recovering some hidden  ... 
doi:10.1016/j.ejor.2012.08.016 fatcat:c27kagfnxnhjfbil2rydhjhomm

AACR/SNMMI State-of-the-Art Molecular Imaging in Cancer Biology and Therapy: Abstracts

2018 Journal of Nuclear Medicine  
the application and use of molecular imaging in cancer biology and therapy.  ...  New this year will be a session for early-career investigators from Jason Lewis on "How to set up a lab and compete for grant funding" and collaboration with the NIH/NCI Quantitative Imaging Network for  ...  The use of PET/CT allowed for accurate diagnosis and early treatment of patients with malignancy, in the long course, will result in lower costs and benefit for the patients.  ... 
doi:10.2967/jnm592abs pmid:29419457 fatcat:ixe3oonuovflloz5ldsvbfv2sm

Intelligence, physics and information – the tradeoff between accuracy and simplicity in machine learning [article]

Tailin Wu
2020 arXiv   pre-print
We address part of this question by introducing an algorithm that combines prediction and minimizing information from the input, for exploratory causal discovery from observational time series.  ...  In this thesis, I address several key questions in some aspects of intelligence, and study the phase transitions in the two-term tradeoff, using strategies and tools from physics and information.  ...  We use noisy label to mimic realistic settings where the data may be noisy and also to have controllable difficulty for different classes.  ... 
arXiv:2001.03780v2 fatcat:piduzlhoafcjhhsgthulbbhtke

Artificial Intelligence : from Research to Application ; the Upper-Rhine Artificial Intelligence Symposium (UR-AI 2019) [article]

Andreas Christ, Franz Quint
2019 arXiv   pre-print
The TriRhenaTech alliance universities and their partners presented their competences in the field of artificial intelligence and their cross-border cooperations with the industry at the tri-national conference  ...  , and Offenburg, the Baden-Wuerttemberg Cooperative State University Loerrach, the French university network Alsace Tech (comprised of 14 'grandes \'ecoles' in the fields of engineering, architecture and  ...  "Process chains in manufacturing" (DFG) and under grant #03FH061PX5 (BMBF).  ... 
arXiv:1903.08495v1 fatcat:3to4wspv3zc6dak6ogjpud5nkq

Internet of Things 2.0: Concepts, Applications, and Future Directions

Ian Zhou, Imran Makhdoom, Negin Shariati, Muhammad Ahmad Raza, Rasool Keshavarz, Justin Lipman, Mehran Abolhasan, Abbas Jamalipour
2021 IEEE Access  
This approach is particularly useful in applications where low-cost and low profile systems are needed or digital solutions are not available, as for instance in very high frequency and high speed ultra-wideband  ...  The authors in [57] gave a generic model of linear regression with multiple outputs.  ... 
doi:10.1109/access.2021.3078549 fatcat:g5jkc5p6tngpfonbhtsbcjipai

Full Issue PDF

2020 JACC: Basic to Translational Science  
The authors attest they are in compliance with human studies committees and animal welfare regulations of the authors' institutions and Food and Drug Administration guidelines, including patient consent  ...  For more information, visit  ...  Regression analyses using simple and multiple linear regression models were adjusted for baseline (week 6) serum cholesterol, C-reactive protein, minimum lumen area, and the respective plaque parameters  ... 
doi:10.1016/s2452-302x(20)30296-5 pmid:32835137 pmcid:PMC7384789 fatcat:6sfux6rj4fgptfrc6akxd2n3by

GIS Mashups [chapter]

Ilya Zaslavsky
2017 Encyclopedia of GIS  
Originally developed for geo-spatial contexts, they are also applicable in general contexts that involve computing and modeling with multi-level spatial aggregates, e.g., modeling a configuration space  ...  We estimate the covariance parameters conditional on the locations for which we have observed data, and use the inferred structure to make predictions at new locations.  ...  These include linear and nonlinear regression between the two components of the regression. To demonstrate, a linear regression is presented below.  ... 
doi:10.1007/978-3-319-17885-1_530 fatcat:rrr5buo3zrevpigdtjwhewipvm

Edge Intelligence: Architectures, Challenges, and Applications [article]

Dianlei Xu, Tong Li, Yong Li, Xiang Su, Sasu Tarkoma, Tao Jiang, Jon Crowcroft, Pan Hui
2020 arXiv   pre-print
Edge intelligence refers to a set of connected systems and devices for data collection, caching, processing, and analysis in locations close to where data is captured based on artificial intelligence.  ...  We then aim for a systematic classification of the state of the solutions by examining research results and observations for each of the four components and present a taxonomy that includes practical problems  ...  In addition to minimum weight and cost functions, there are efforts trying to prune with the metric of energy consumption.  ... 
arXiv:2003.12172v2 fatcat:xbrylsvb7bey5idirunacux6pe

Scintigraphic assessments of the reparative process in osteonecrosis of the femoral head using SPECT/CT with 99mTc hydroxymethylene diphosphonate

Goro Motomura, Takuaki Yamamoto, Koichiro Abe, Yasuharu Nakashima, Masanobu Ohishi, Satoshi Hamai, Toshio Doi, Hiroshi Honda, Yukihide Iwamoto
2014 Nuclear medicine communications  
than one hour, thereby producing a potentially time-saving and cost-saving alternative.  ...  Additionally, a high linear correlation coefficient in the SUV mean for the PET images form PET/CT and PET/MR was found.  ...  All these patients were clinically asymptomatic for brain metastases at the time of the study, and hence MR brain would not have been done.  ... 
doi:10.1097/mnm.0000000000000166 pmid:25076160 fatcat:mzflxyz2fjephb3xksxtrp7xqa

Interactive Learning for Sequential Decisions and Predictions

Stephane Ross
2018
Sequential prediction problems arise commonly in many areas of robotics and information processing: e.g., predicting a sequence of actions over time to achieve a goal in a control task, interpreting an  ...  a simulated helicopter for controller synthesis, [...]  ...  This presented set of features can be computed at 15 Hz using the graphics processing unit (GPU) for dense optical flow computation.  ... 
doi:10.1184/r1/6720269.v1 fatcat:d33g5bggubf4fpctsujichxue4
« Previous Showing results 1 — 15 out of 38 results