Skip to content

Learning Multiple Layers of Features from Tiny Images

Alex Krizhevsky

2024 · 23,889 citationsOpen access

No retraction on record in OpenAlex.Check Crossref now

Cite this paper

Krizhevsky, A. (2024). Learning multiple layers of features from tiny images. https://doi.org/10.57702/zp44cu3g

In text: (Krizhevsky, 2024)

Ask a question about this research

One question, free, no account. Anchorcite finds the papers, checks each against Crossref and links every sentence of the answer to the passage it comes from.

Abstract

April 8, 2009Groups at MIT and NYU have collected a dataset of millions of tiny colour images from the web. It is, in principle, an excellent dataset for unsupervised training of deep generative models, but previous researchers who have tried this have found it di cult to learn a good set of lters from the images. We show how to train a multi-layer generative model that learns to extract meaningful features which resemble those found in the human visual cortex. Using a novel parallelization algorithm to distribute the work among multiple machines connected on a network, we show how training such a model can be done in reasonable time. A second problematic aspect of the tiny images dataset is that there are no reliable class labels which makes it hard to use for object recognition experiments. We created two sets of reliable labels. The CIFAR-10 set has 6000 examples of each of 10 classes and the CIFAR-100 set has 600 examples of each of 100 non-overlapping classes. Using these labels, we show that object recognition is signi cantly

  1. Deep Residual Learning for Image Recognition2016
  2. ImageNet classification with deep convolutional neural networks2017
  3. Going deeper with convolutions2015
  4. Densely Connected Convolutional Networks2017
  5. Fully convolutional networks for semantic segmentation2015

Metadata from OpenAlex (CC0). Citations are generated from the published record.