Deep learning-Using machine learning to study biological vision

Najib J. Majaj, Denis Pelli

Research output: Contribution to journalArticle

Abstract

Many vision science studies employ machine learning, especially the version called "deep learning." Neuroscientists use machine learning to decode neural responses. Perception scientists try to understand how living organisms recognize objects. To them, deep neural networks offer benchmark accuracies for recognition of learned stimuli. Originally machine learning was inspired by the brain. Today, machine learning is used as a statistical tool to decode brain activity. Tomorrow, deep neural networks might become our best model of brain function. This brief overview of the use of machine learning in biological vision touches on its strengths, weaknesses, milestones, controversies, and current directions. Here, we hope to help vision scientists assess what role machine learning should play in their research.

Original languageEnglish (US)
Article number2
Pages (from-to)1-13
Number of pages13
JournalJournal of Vision
Volume18
Issue number13
DOIs
StatePublished - Dec 1 2018

Fingerprint

Learning
Brain
Benchmarking
Machine Learning
Research

Keywords

  • Deep learning
  • Machine learning
  • Neural networks
  • Object recognition

ASJC Scopus subject areas

  • Ophthalmology
  • Sensory Systems

Cite this

Deep learning-Using machine learning to study biological vision. / Majaj, Najib J.; Pelli, Denis.

In: Journal of Vision, Vol. 18, No. 13, 2, 01.12.2018, p. 1-13.

Research output: Contribution to journalArticle

@article{91a7a030a51d494e8ba235fe3d86b18c,
title = "Deep learning-Using machine learning to study biological vision",
abstract = "Many vision science studies employ machine learning, especially the version called {"}deep learning.{"} Neuroscientists use machine learning to decode neural responses. Perception scientists try to understand how living organisms recognize objects. To them, deep neural networks offer benchmark accuracies for recognition of learned stimuli. Originally machine learning was inspired by the brain. Today, machine learning is used as a statistical tool to decode brain activity. Tomorrow, deep neural networks might become our best model of brain function. This brief overview of the use of machine learning in biological vision touches on its strengths, weaknesses, milestones, controversies, and current directions. Here, we hope to help vision scientists assess what role machine learning should play in their research.",
keywords = "Deep learning, Machine learning, Neural networks, Object recognition",
author = "Majaj, {Najib J.} and Denis Pelli",
year = "2018",
month = "12",
day = "1",
doi = "10.1167/18.13.2",
language = "English (US)",
volume = "18",
pages = "1--13",
journal = "Journal of Vision",
issn = "1534-7362",
publisher = "Association for Research in Vision and Ophthalmology Inc.",
number = "13",

}

TY - JOUR

T1 - Deep learning-Using machine learning to study biological vision

AU - Majaj, Najib J.

AU - Pelli, Denis

PY - 2018/12/1

Y1 - 2018/12/1

N2 - Many vision science studies employ machine learning, especially the version called "deep learning." Neuroscientists use machine learning to decode neural responses. Perception scientists try to understand how living organisms recognize objects. To them, deep neural networks offer benchmark accuracies for recognition of learned stimuli. Originally machine learning was inspired by the brain. Today, machine learning is used as a statistical tool to decode brain activity. Tomorrow, deep neural networks might become our best model of brain function. This brief overview of the use of machine learning in biological vision touches on its strengths, weaknesses, milestones, controversies, and current directions. Here, we hope to help vision scientists assess what role machine learning should play in their research.

AB - Many vision science studies employ machine learning, especially the version called "deep learning." Neuroscientists use machine learning to decode neural responses. Perception scientists try to understand how living organisms recognize objects. To them, deep neural networks offer benchmark accuracies for recognition of learned stimuli. Originally machine learning was inspired by the brain. Today, machine learning is used as a statistical tool to decode brain activity. Tomorrow, deep neural networks might become our best model of brain function. This brief overview of the use of machine learning in biological vision touches on its strengths, weaknesses, milestones, controversies, and current directions. Here, we hope to help vision scientists assess what role machine learning should play in their research.

KW - Deep learning

KW - Machine learning

KW - Neural networks

KW - Object recognition

UR - http://www.scopus.com/inward/record.url?scp=85058464110&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058464110&partnerID=8YFLogxK

U2 - 10.1167/18.13.2

DO - 10.1167/18.13.2

M3 - Article

VL - 18

SP - 1

EP - 13

JO - Journal of Vision

JF - Journal of Vision

SN - 1534-7362

IS - 13

M1 - 2

ER -