Multi-column deep neural networks for image classification

Traditional methods of computer vision and machine learning cannot match human performance on tasks such as the recognition of handwritten digits or traffic signs. Our biologically plausible, wide and deep artificial neural network architectures can. Small (often minimal) receptive fields of convolu...

Full description

Saved in:
Bibliographic Details
Published in:2012 IEEE Conference on Computer Vision and Pattern Recognition pp. 3642 - 3649
Main Authors: Ciresan, D., Meier, U., Schmidhuber, J.
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2012
Subjects:
Benchmark testing
Computer architecture
Error analysis
Graphics processing unit
Neurons
Training
ISBN:9781467312264, 1467312266
ISSN:1063-6919, 1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Traditional methods of computer vision and machine learning cannot match human performance on tasks such as the recognition of handwritten digits or traffic signs. Our biologically plausible, wide and deep artificial neural network architectures can. Small (often minimal) receptive fields of convolutional winner-take-all neurons yield large network depth, resulting in roughly as many sparsely connected neural layers as found in mammals between retina and visual cortex. Only winner neurons are trained. Several deep neural columns become experts on inputs preprocessed in different ways; their predictions are averaged. Graphics cards allow for fast training. On the very competitive MNIST handwriting benchmark, our method is the first to achieve near-human performance. On a traffic sign recognition benchmark it outperforms humans by a factor of two. We also improve the state-of-the-art on a plethora of common image classification benchmarks.
ISBN:9781467312264
1467312266
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2012.6248110