34,691 Hits in 6.8 sec

Energy-efficient Machine Learning in Silicon: A Communications-inspired Approach [article]

Naresh R. Shanbhag
2016 arXiv   pre-print
This position paper advocates a communications-inspired approach to the design of machine learning systems on energy-constrained embedded 'always-on' platforms.  ...  The communications-inspired approach has the potential to fully leverage the opportunities afforded by ML algorithms and applications in order to address the challenges inherent in their deployment on  ...  based on statistical estimation and detection.  ... 
arXiv:1611.03109v1 fatcat:qdnks33xmzcrdkez43z2kicxeq

Forming Ensembles at Runtime: A Machine Learning Approach [chapter]

Tomáš Bureš, Ilias Gerostathopoulos, Petr Hnětynka, Jan Pacovský
2020 Lecture Notes in Computer Science  
To tackle this problem, in this paper we propose to recast the ensemble formation problem as a classification problem and use machine learning to efficiently form ensembles at scale.  ...  This poses a serious limitation to the use of ensembles in large-scale and partially uncertain SSAs.  ...  We are also grateful to Milan Straka from Institute of Formal and Applied Linguistics at Faculty of Mathematics and Physics at Charles University for valuable input in the field of deep networks that improved  ... 
doi:10.1007/978-3-030-61470-6_26 fatcat:mvm2lwmuoje2zclc7ja2zyfsfm

Optimal Targeting in Fundraising: A Causal Machine-Learning Approach [article]

Tobias Cagala, Ulrich Glogowsky, Johannes Rincke, Anthony Strittmatter
2021 arXiv   pre-print
We combine a field experiment and a causal machine-learning approach to increase a charity's fundraising effectiveness.  ...  Our results demonstrate that machine-learning-based optimal targeting allows the charity to substantially increase donations net of fundraising costs relative to uniform benchmarks in which either everybody  ...  Experimental Design and Data Our approach to derive a machine-learning-based optimal targeting rule proceeds in three steps.  ... 
arXiv:2103.10251v3 fatcat:sk3nxufzyvfzrp2mdnjqjey5iy

Cryptomining Makes Noise: a Machine Learning Approach for Cryptojacking Detection [article]

Maurantonio Caprolu, Simone Raponi, Gabriele Oligeri, Roberto Di Pietro
2020 arXiv   pre-print
In this paper, we propose a network-based approach to detect and identify crypto-clients activities by solely relying on the network traffic, even when encrypted.  ...  Then, we propose Crypto-Aegis, a Machine Learning (ML) based framework built over the results of our investigation, aimed at detecting cryptocurrencies related activities, e.g., pool mining, solo mining  ...  The information and views set out in this publication are those of the authors and do not necessarily reflect the official opinion of the QNRF.  ... 
arXiv:1910.09272v2 fatcat:42pbrpglnjg37kxdqr74dfkbri

A machine learning approach to TCP state monitoring from passive measurements

Desta Haileselassie Hagos, Paal E. Engelstad, Anis Yazidi, Oivind Kure
2018 2018 Wireless Days (WD)  
We gratefully acknowledge the reviewers for their helpful feedback and detailed comments.  ...  We would like to thank the Research Infrastructure Services Group at the University of Oslo for the use of multicore cluster machines.  ...  In Paper II, we presented a machine learning-based approach to identify the underlying traditional loss-based TCP variants which achieve a reasonably good accuracy on emulated and realistic scenarios.  ... 
doi:10.1109/wd.2018.8361713 dblp:conf/wd/HagosEYK18 fatcat:hmeh7nfa7bbwxnncel5xnyytim

Game-Theoretic and Machine Learning-based Approaches for Defensive Deception: A Survey [article]

Mu Zhu, Ahmed H. Anwar, Zelin Wan, Jin-Hee Cho, Charles Kamhoua, Munindar P. Singh
2021 arXiv   pre-print
This survey paper focuses on defensive deception research centered on game theory and machine learning, since these are prominent families of artificial intelligence approaches that are widely employed  ...  Although defensive deception is increasingly popular in the research community, there has not been a systematic investigation of its key components, the underlying principles, and its tradeoffs in various  ...  The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Army Research Laboratory  ... 
arXiv:2101.10121v2 fatcat:ko2mzzvyerehnfxbwgeuz72ilu

A review of machine learning approaches to Spam filtering

Thiago S. Guzella, Walmir M. Caminhas
2009 Expert systems with applications  
In this paper, we present a comprehensive review of recent developments in the application of machine learning algorithms to Spam filtering, focusing on both textual-and image-based approaches.  ...  Two particularly important aspects not widely recognized in the literature are discussed: the difficulties in updating a classifier based on the bag-of-words representation and a major difference between  ...  Acknowledgements This work was supported by grants from UOL, through its Bolsa Pesquisa program (process number 20060519110414a), FAPEMIG and CNPq.  ... 
doi:10.1016/j.eswa.2009.02.037 fatcat:gf5z34w6arcdzh2w36tgefqppa

A Review of Recent Deep Learning Approaches in Human-Centered Machine Learning

Tharindu Kaluarachchi, Andrew Reis, Suranga Nanayakkara
2021 Sensors  
These concerns, coupled with the increasing human-AI interactions, have created the emerging field that is Human-Centered Machine Learning (HCML).  ...  Deep Learning has generated complexities in algorithms, and researchers and users have raised concerns regarding the usability and adoptability of Deep Learning systems.  ...  We also thank Gimhani Pemarathne for their support to proofread and edit. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s21072514 pmid:33916850 pmcid:PMC8038476 fatcat:wvn3av6e2nf7hdxrswfmyyt2te

Diagnosis of Series DC Arc Faults—A Machine Learning Approach

Rory David Telford, Stuart Galloway, Bruce Stephen, Ian Elders
2017 IEEE Transactions on Industrial Informatics  
Inte-lArc combines time-frequency and time-domain extracted features with hidden Markov models (HMMs) to discriminate between nominal transient behavior and arc fault behavior across a variety of operating  ...  Abstract-Increasing prevalence of dc sources and loads has resulted in dc distribution being reconsidered at a microgrid level.  ...  Consequently, this paper proposes IntelArc, a machine learning (ML) based system that uses extracted features to train HMM and increases the potential for an accurate and generalized diagnostic performance  ... 
doi:10.1109/tii.2016.2633335 fatcat:anp33ouft5emtdz2uo5k5n3txm

Mobile Collaborative Spectrum Sensing for Heterogeneous Networks: A Bayesian Machine Learning Approach

Yizhen Xu, Peng Cheng, Zhuo Chen, Yonghui Li, Branka Vucetic
2018 IEEE Transactions on Signal Processing  
To tackle this problem, in this paper, we propose a new framework based on Bayesian machine learning.  ...  We first develop a novel non-parametric Bayesian learning model, referred to as beta process sticky hidden Markov model (BP-SHMM), to capture the spatial-temporal correlation in the collected spectrum  ...  [21] In this paper, we propose a novel learning-based mobile CSS framework for large-scale heterogeneous CRNs, drawing upon the recent advances in Bayesian machine learning.  ... 
doi:10.1109/tsp.2018.2870379 fatcat:2kp46vn4pzbv7cedr2y4kz2n64

Extending the Machine Learning Abstraction Boundary: A Complex Systems Approach to Incorporate Societal Context [article]

Donald Martin Jr., Vinodkumar Prabhakaran, Jill Kuhlberg, Andrew Smart, William S. Isaac
2020 arXiv   pre-print
Machine learning (ML) fairness research tends to focus primarily on mathematically-based interventions on often opaque algorithms or models and/or their immediate inputs and outputs.  ...  Finally, we identify community based system dynamics (CBSD) as a powerful, transparent and rigorous approach for practicing CCTF during all phases of the ML product development process.  ...  We would like to thank Emily Denton, Ben Hutchinson, Sean Legassick, Silvia Chiappa, Matt Botvinick, Reena Jana, Dierdre Mulligan, and Deborah Raji for their valuable feedback on this paper.  ... 
arXiv:2006.09663v1 fatcat:oelh2r2m7nbqldypsb4bg6p6qe

A Big Data and machine learning approach for network monitoring and security

Leonardo Maccari, Andrea Passerini
2018 Security and Privacy  
KEYWORDS big data, machine learning, mesh networks, network monitoring, root cause analysis INTRODUCTION Wireless mesh networks have attracted in the past a large attention from researchers, but today,  ...  This paper explains how today we can perform monitoring, anomaly detection and root cause analysis in mesh networks using Big Data techniques.  ...  them, primarily based on machine learning approaches.  ... 
doi:10.1002/spy2.53 fatcat:gu7a2noqbng4bmvzksypyp4ibu

A Bayesian Approach to Policy Recognition and State Representation Learning

Adrian Sosic, Abdelhak M. Zoubir, Heinz Koeppl
2018 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Moreover, we show that our methodology can be applied in a nonparametric context to infer the complexity of the state representation used by the expert, and to learn task-appropriate partitionings of the  ...  Learning from demonstration (LfD) is the process of building behavioral models of a task from demonstrations provided by an expert.  ...  The authors of [19] presented a nonparametric inverse reinforcement learning approach to cluster the expert data based on a set of learned subgoals encoded in the form of local rewards.  ... 
doi:10.1109/tpami.2017.2711024 pmid:28622668 fatcat:p6v47ligevczjhoza52axht234

Detection of Username Enumeration Attack on SSH Protocol: Machine Learning Approach

Abel Z. Agghey, Lunodzo J. Mwinuka, Sanket M. Pandhare, Mussa A. Dida, Jema D. Ndibwile
2021 Symmetry  
We apply four asymmetrical classifiers on our generated dataset collected from a closed-environment network to build machine-learning-based models for attack detection.  ...  Our results show that machine-learning approaches to detect SSH username enumeration attacks were quite successful, with KNN having an accuracy of 99.93%, NB 95.70%, RF 99.92%, and DT 99.88%.  ...  The emergence of attacks and malicious behaviors pose a significant danger to computer security [8] .  ... 
doi:10.3390/sym13112192 fatcat:22rtu2rucnbpxjytrpxkm7xzdq

A scalable sparse Cholesky based approach for learning high-dimensional covariance matrices in ordered data

Kshitij Khare, Sang-Yun Oh, Syed Rahman, Bala Rajaratnam
2019 Machine Learning  
Acknowledgment We have been fortunate to have our colleagues and collaborators give us their impressions and contributions toward the contents of this book. We would like to  ...  Other machine learning outlier detection strategies include those based on clustering.  ...  Popular approaches include statistical, neural network, machine learning, and hybrid system models. ese approaches, described below, encompass distance-based, set-based, density-based, depth-based, model-based  ... 
doi:10.1007/s10994-019-05810-5 fatcat:nulmjvxvwjgojfoe2ywv3pjrpu
« Previous Showing results 1 — 15 out of 34,691 results