Learning Multiple Layers of Features from Tiny Images

April 8, 2009Groups at MIT and NYU have collected a dataset of millions of tiny colour images from the web. 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.

⚡ This is an original paraphrased summary — not copied from the abstract. Full paper available at the source link below.

• 1 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.
• 2 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.
• 3 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.

This research advances how AI systems learn, reason, and solve problems — with direct implications for automation and scientific discovery.

This summary is based on publicly available metadata and abstract. For the full research paper, visit the original source: