Deep, big, simple neural nets for handwritten digit recognition

Dan Claudiu Cireşan; Ueli Meier; Luca Maria Gambardella; Jürgen Schmidhuber

doi:10.1162/NECO_a_00052

Deep, big, simple neural nets for handwritten digit recognition

Dan Claudiu Cireşan, Ueli Meier, Luca Maria Gambardella, Jürgen Schmidhuber

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

757 Scopus citations

Abstract

Good old online backpropagation for plain multilayer perceptrons yields a very low 0.35% error rate on the MNIST handwritten digits benchmark. All we need to achieve this best result so far are many hidden layers, many neurons per layer, numerous deformed training images to avoid overfitting, and graphics cards to greatly speed up learning. © 2010 Massachusetts Institute of Technology.

Original language	English (US)
Pages (from-to)	3207-3220
Number of pages	14
Journal	Neural Computation
Volume	22
Issue number	12
DOIs	https://doi.org/10.1162/NECO_a_00052
State	Published - Dec 1 2010
Externally published	Yes

ASJC Scopus subject areas

Cognitive Neuroscience

Access to Document

10.1162/NECO_a_00052

Cite this

@article{6c3b1ad0a1a44b65af792fc54075f08e,

title = "Deep, big, simple neural nets for handwritten digit recognition",

abstract = "Good old online backpropagation for plain multilayer perceptrons yields a very low 0.35% error rate on the MNIST handwritten digits benchmark. All we need to achieve this best result so far are many hidden layers, many neurons per layer, numerous deformed training images to avoid overfitting, and graphics cards to greatly speed up learning. {\textcopyright} 2010 Massachusetts Institute of Technology.",

author = "Cire{\c s}an, {Dan Claudiu} and Ueli Meier and Gambardella, {Luca Maria} and J{\"u}rgen Schmidhuber",

note = "Generated from Scopus record by KAUST IRTS on 2022-09-14",

year = "2010",

month = dec,

day = "1",

doi = "10.1162/NECO_a_00052",

language = "English (US)",

volume = "22",

pages = "3207--3220",

journal = "Neural Computation",

issn = "0899-7667",

publisher = "MIT Press Journals",

number = "12",

}

TY - JOUR

T1 - Deep, big, simple neural nets for handwritten digit recognition

AU - Cireşan, Dan Claudiu

AU - Meier, Ueli

AU - Gambardella, Luca Maria

AU - Schmidhuber, Jürgen

N1 - Generated from Scopus record by KAUST IRTS on 2022-09-14

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Good old online backpropagation for plain multilayer perceptrons yields a very low 0.35% error rate on the MNIST handwritten digits benchmark. All we need to achieve this best result so far are many hidden layers, many neurons per layer, numerous deformed training images to avoid overfitting, and graphics cards to greatly speed up learning. © 2010 Massachusetts Institute of Technology.

AB - Good old online backpropagation for plain multilayer perceptrons yields a very low 0.35% error rate on the MNIST handwritten digits benchmark. All we need to achieve this best result so far are many hidden layers, many neurons per layer, numerous deformed training images to avoid overfitting, and graphics cards to greatly speed up learning. © 2010 Massachusetts Institute of Technology.

UR - https://direct.mit.edu/neco/article/22/12/3207-3220/7596

UR - http://www.scopus.com/inward/record.url?scp=78649669320&partnerID=8YFLogxK

U2 - 10.1162/NECO_a_00052

DO - 10.1162/NECO_a_00052

M3 - Article

SN - 0899-7667

VL - 22

SP - 3207

EP - 3220

JO - Neural Computation

JF - Neural Computation

IS - 12

ER -

Deep, big, simple neural nets for handwritten digit recognition

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this