CIFAR-10

Software / App

A simpler dataset of small icons with ten categories, commonly used to explore basic convolutional neural networks.

Mentioned in 2 videos

Videos Mentioning CIFAR-10

MIT 6.S094: Computer Vision

MIT 6.S094: Computer Vision

Lex Fridman

A simpler dataset of small icons with ten categories, commonly used to explore basic convolutional neural networks.

MIT 6.S094: Convolutional Neural Networks for End-to-End Learning of the Driving Task

MIT 6.S094: Convolutional Neural Networks for End-to-End Learning of the Driving Task

Lex Fridman

A dataset of small images with 10 categories, used for quick algorithm testing and proving concepts. Human performance is around 94% accuracy, while CNNs achieve 95.4%.