Principled machine learning

Yordan Raykov; David Saad

doi:10.1109/JSTQE.2022.3186798

Principled machine learning

Yordan Raykov
, David Saad

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

86 Downloads (Pure)

Abstract

We introduce the underlying concepts which give rise to some of the commonly used machine learning methods, excluding deep-learning machines and neural networks. We point to their advantages, limitations and potential use in various areas of photonics. The main methods covered include parametric and non-parametric regression and classification techniques, kernel-based methods and support vector machines, decision trees, probabilistic models, Bayesian graphs, mixture models, Gaussian processes, message passing methods and visual informatics.

Original language	English
Article number	0200419
Number of pages	19
Journal	IEEE Journal of Selected Topics in Quantum Electronics
Volume	28
Issue number	4
Early online date	27 Jun 2022
DOIs	https://doi.org/10.1109/JSTQE.2022.3186798
Publication status	Published - 31 Jul 2022

Bibliographical note

UKRI Rights Retention: For the purpose of open access, the author has applied a Creative Commons Attribution (CC BY) licence to any Author Accepted Manuscript version arising

Funding: DS acknowledges support from the EPSRC Programme Grant TRANSNET (EP/R035342/1) and the Leverhulme trust (RPG-2018-092). YR acknowledges support by the EPSRC Horizon Digital Economy Research grant ‘Trusted Data Driven Products: EP/T022493/1 and grant ‘From Human Data to Personal Experience’: EP/M02315X/1.

Keywords

Channel estimation
Computational modeling
Kernel
Machine learning
Neural networks
Probabilistic logic
Statistical machine learning
Visualization
deciion trees
dimensionality reduction
kernel-based methods
message passing techniques
probabilistic methods
visual informatics

Access to Document

10.1109/JSTQE.2022.3186798

Machine_Learning_without_neural_networks__JSTQE_
UKRI Rights Retention: For the purpose of open access, the author has applied a Creative Commons Attribution (CC BY) licence to any Author Accepted Manuscript version arising
Accepted author manuscript, 1.11 MBLicence: CC BY 4.0

Cite this

@article{641fc727b7b34cfba277783cba18686b,

title = "Principled machine learning",

abstract = "We introduce the underlying concepts which give rise to some of the commonly used machine learning methods, excluding deep-learning machines and neural networks. We point to their advantages, limitations and potential use in various areas of photonics. The main methods covered include parametric and non-parametric regression and classification techniques, kernel-based methods and support vector machines, decision trees, probabilistic models, Bayesian graphs, mixture models, Gaussian processes, message passing methods and visual informatics.",

keywords = "Channel estimation, Computational modeling, Kernel, Machine learning, Neural networks, Probabilistic logic, Statistical machine learning, Visualization, deciion trees, dimensionality reduction, kernel-based methods, message passing techniques, probabilistic methods, visual informatics",

author = "Yordan Raykov and David Saad",

note = "UKRI Rights Retention: For the purpose of open access, the author has applied a Creative Commons Attribution (CC BY) licence to any Author Accepted Manuscript version arising Funding: DS acknowledges support from the EPSRC Programme Grant TRANSNET (EP/R035342/1) and the Leverhulme trust (RPG-2018-092). YR acknowledges support by the EPSRC Horizon Digital Economy Research grant {\textquoteleft}Trusted Data Driven Products: EP/T022493/1 and grant {\textquoteleft}From Human Data to Personal Experience{\textquoteright}: EP/M02315X/1. ",

year = "2022",

month = jul,

day = "31",

doi = "10.1109/JSTQE.2022.3186798",

language = "English",

volume = "28",

journal = "IEEE Journal of Selected Topics in Quantum Electronics",

issn = "1077-260X",

publisher = "IEEE",

number = "4",

}

TY - JOUR

T1 - Principled machine learning

AU - Raykov, Yordan

AU - Saad, David

N1 - UKRI Rights Retention: For the purpose of open access, the author has applied a Creative Commons Attribution (CC BY) licence to any Author Accepted Manuscript version arising Funding: DS acknowledges support from the EPSRC Programme Grant TRANSNET (EP/R035342/1) and the Leverhulme trust (RPG-2018-092). YR acknowledges support by the EPSRC Horizon Digital Economy Research grant ‘Trusted Data Driven Products: EP/T022493/1 and grant ‘From Human Data to Personal Experience’: EP/M02315X/1.

PY - 2022/7/31

Y1 - 2022/7/31

N2 - We introduce the underlying concepts which give rise to some of the commonly used machine learning methods, excluding deep-learning machines and neural networks. We point to their advantages, limitations and potential use in various areas of photonics. The main methods covered include parametric and non-parametric regression and classification techniques, kernel-based methods and support vector machines, decision trees, probabilistic models, Bayesian graphs, mixture models, Gaussian processes, message passing methods and visual informatics.

AB - We introduce the underlying concepts which give rise to some of the commonly used machine learning methods, excluding deep-learning machines and neural networks. We point to their advantages, limitations and potential use in various areas of photonics. The main methods covered include parametric and non-parametric regression and classification techniques, kernel-based methods and support vector machines, decision trees, probabilistic models, Bayesian graphs, mixture models, Gaussian processes, message passing methods and visual informatics.

KW - Channel estimation

KW - Computational modeling

KW - Kernel

KW - Machine learning

KW - Neural networks

KW - Probabilistic logic

KW - Statistical machine learning

KW - Visualization

KW - deciion trees

KW - dimensionality reduction

KW - kernel-based methods

KW - message passing techniques

KW - probabilistic methods

KW - visual informatics

UR - https://ieeexplore.ieee.org/document/9808310

UR - https://www.scopus.com/pages/publications/85133747452

U2 - 10.1109/JSTQE.2022.3186798

DO - 10.1109/JSTQE.2022.3186798

M3 - Article

AN - SCOPUS:85133747452

SN - 1077-260X

VL - 28

JO - IEEE Journal of Selected Topics in Quantum Electronics

JF - IEEE Journal of Selected Topics in Quantum Electronics

IS - 4

M1 - 0200419

ER -

Principled machine learning

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this