2010 ConvolutionalDeepBeliefNetworks

• (Krizhevsky & Hinton, 2010) ⇒ Alex Krizhevsky, and Geoffrey E. Hinton. (2010). “Convolutional Deep Belief Networks on Cifar-10.” In: Unpublished manuscript, 40.

Subject Headings: CIFAR-10 Dataset.

Cited By

• http://scholar.google.com/scholar?q=%222010%22+Convolutional+Deep+Belief+Networks+on+Cifar-10

Quotes

Introduction

We describe how to train a two-layer convolutional Deep Belief Network (DBN) on the 1.6 million tiny images dataset. When training a convolutional DBN, one must decide what to do with the edge pixels of the images. As the pixels near the edge of an image contribute to the fewest convolutional filter outputs, the model may see it fit to tailor its few convolutional filters to better model the edge pixels. This is undesirable because it usually comes at the expense of a good model for the interior parts of the image. We investigate several ways of dealing with the edge pixels when training a convolutional DBN. Using a combination of locally-connected convolutional units and globally-connected units, as well as a few tricks to reduce the effects of overfitting, we achieve state-of-the-art performance in the classification task of the CIFAR-10 subset of the tiny images dataset.

References

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2010 ConvolutionalDeepBeliefNetworks	Geoffrey E. Hinton Alex Krizhevsky			Convolutional Deep Belief Networks on Cifar-10						2010