Paper · 2024 · Open access
Learning Multiple Layers of Features from Tiny Images
http://www.cs.toronto.edu/%7Ekriz/learning-features-2009-TR.pdf · Published 1 January 2024 · DOI 10.57702/zp44cu3g
In brief
“Learning Multiple Layers of Features from Tiny Images” is a 2024 paper by Alex Krizhevsky, published in http://www.cs.toronto.edu/%7Ekriz/learning-features-2009-TR.pdf. OpenAlex counts 23,884 citations as of 15 November 2026, which puts it in the top 1% of works published in 2024 by citations. It is open access: the full text is free to read at TIB Data Manager.
- Citations
- 23,884
- Most cited in
- 2021 (4,430)
- Field-weighted impact
- 427.00
- References
- 3
- Authors
- 1
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
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Krizhevsky, A. (2024). Learning Multiple Layers of Features from Tiny Images. http://www.cs.toronto.edu/%7Ekriz/learning-features-2009-TR.pdf. https://doi.org/10.57702/zp44cu3g
MLA 9
Krizhevsky, Alex. “Learning Multiple Layers of Features from Tiny Images.” http://www.cs.toronto.edu/%7Ekriz/learning-features-2009-TR.pdf, 2024. https://doi.org/10.57702/zp44cu3g.
Chicago
Krizhevsky, Alex. 2024. “Learning Multiple Layers of Features from Tiny Images.” http://www.cs.toronto.edu/%7Ekriz/learning-features-2009-TR.pdf. https://doi.org/10.57702/zp44cu3g.
Harvard
Krizhevsky, A. (2024) ‘Learning Multiple Layers of Features from Tiny Images’, http://www.cs.toronto.edu/%7Ekriz/learning-features-2009-TR.pdf. doi:10.57702/zp44cu3g.
IEEE
A. Krizhevsky, “Learning Multiple Layers of Features from Tiny Images,” http://www.cs.toronto.edu/%7Ekriz/learning-features-2009-TR.pdf, 2024, doi: 10.57702/zp44cu3g.
BibTeX
@article{krizhevsky2024learning,
title = {{Learning Multiple Layers of Features from Tiny Images}},
author = {Krizhevsky, Alex},
journal = {http://www.cs.toronto.edu/\%7Ekriz/learning-features-2009-TR.pdf},
year = {2024},
doi = {10.57702/zp44cu3g},
url = {https://doi.org/10.57702/zp44cu3g}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2017 | 844 | |
| 2018 | 1,490 | |
| 2019 | 2,419 | |
| 2020 | 3,371 | |
| 2021 | 4,430 | |
| 2022 | 2,894 | |
| 2023 | 3,369 | |
| 2024 | 2,945 | |
| 2025 | 1,074 | |
| 2026 | 26 |
Its field-weighted citation impact is 427.00: it has been cited 427.00 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- deep generative models
- unsupervised feature learning
- human visual cortex
- distributed training
- CIFAR-10
- CIFAR-100
- object recognition
- image classification
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Krizhevsky, A. (2024). Learning Multiple Layers of Features from Tiny Images. http://www.cs.toronto.edu/%7Ekriz/learning-features-2009-TR.pdf. https://doi.org/10.57702/zp44cu3g
How many times has this paper been cited?
23,884 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access: read the free full text at TIB Data Manager.
Who wrote this paper?
Alex Krizhevsky.
What is the DOI of this paper?
10.57702/zp44cu3g. The permanent link is https://doi.org/10.57702/zp44cu3g.
Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.