Comprehensive assessment methods are key to progress in deep learning

Michael W. Spratling

doi:10.1017/S0140525X23001668

Comprehensive assessment methods are key to progress in deep learning

Michael W. Spratling^*

^*Corresponding author for this work

King's College London

Research output: Contribution to journal › Review article › peer-review

Abstract

Bowers et al. eloquently describe issues with current deep neural network (DNN) models of vision, claiming that there are deficits both with the methods of assessment, and with the models themselves. I am in agreement with both these claims, but propose a different recipe to the one outlined in the target article for overcoming these issues.

Original language	English
Article number	e407
Journal	Behavioral and Brain Sciences
Volume	46
DOIs	https://doi.org/10.1017/S0140525X23001668
Publication status	Published - 6 Dec 2023

Access to Document

10.1017/S0140525X23001668

Cite this

@article{bc90464091ae4ed49ed55eb1089ead07,

title = "Comprehensive assessment methods are key to progress in deep learning",

abstract = "Bowers et al. eloquently describe issues with current deep neural network (DNN) models of vision, claiming that there are deficits both with the methods of assessment, and with the models themselves. I am in agreement with both these claims, but propose a different recipe to the one outlined in the target article for overcoming these issues.",

author = "Spratling, {Michael W.}",

note = "Publisher Copyright: Copyright {\textcopyright} The Author(s), 2023.",

year = "2023",

month = dec,

day = "6",

doi = "10.1017/S0140525X23001668",

language = "English",

volume = "46",

journal = "Behavioral and Brain Sciences",

issn = "0140-525X",

publisher = "Cambridge University Press",

}

TY - JOUR

T1 - Comprehensive assessment methods are key to progress in deep learning

AU - Spratling, Michael W.

PY - 2023/12/6

Y1 - 2023/12/6

N2 - Bowers et al. eloquently describe issues with current deep neural network (DNN) models of vision, claiming that there are deficits both with the methods of assessment, and with the models themselves. I am in agreement with both these claims, but propose a different recipe to the one outlined in the target article for overcoming these issues.

AB - Bowers et al. eloquently describe issues with current deep neural network (DNN) models of vision, claiming that there are deficits both with the methods of assessment, and with the models themselves. I am in agreement with both these claims, but propose a different recipe to the one outlined in the target article for overcoming these issues.

UR - http://www.scopus.com/inward/record.url?scp=85178850971&partnerID=8YFLogxK

U2 - 10.1017/S0140525X23001668

DO - 10.1017/S0140525X23001668

M3 - Review article

C2 - 38054334

AN - SCOPUS:85178850971

SN - 0140-525X

VL - 46

JO - Behavioral and Brain Sciences

JF - Behavioral and Brain Sciences

M1 - e407

ER -

Comprehensive assessment methods are key to progress in deep learning

Abstract

Access to Document

Other files and links

Fingerprint

Cite this