Lably
Skip to content

CIFAR-10

Image dataset

  • 1 min read
  • 2 chapters

Related on Lably

Through Machine learning, Computer vision and Convolutional neural network

LabDecision Trees & Random ForestsLabDecision Trees & Random ForestsLab · Class 11Machine Learning BasicsLab · Class 10–11Reinforcement Learning Basics

Computer algorithms for recognizing objects in photos often learn by example. CIFAR-10 is a set of images that can be used to teach a computer how to recognize objects. Since the images in CIFAR-10 are low-resolution (32x32), this dataset can allow researchers to quickly try different algorithms to see what works.

CIFAR-10 is a labeled subset of the 80 Million Tiny Images dataset from 2008, published in 2009. When the dataset was created, students were paid to label all of the images.

Various kinds of convolutional neural networks tend to be the best at recognizing the images in CIFAR-10.

Research papers claiming state-of-the-art results on CIFAR-10

This is a table of some of the research papers that claim to have achieved state-of-the-art results on the CIFAR-10 dataset. Not all papers are standardized on the same pre-processing techniques, like image flipping or image shifting. For that reason, it is possible that one paper's claim of state-of-the-art could have a higher error rate than an older state-of-the-art claim but still be valid.

Sign in to keep reading

One more chapter is free with a Lably account.

More in Neuroscience

StriatumNucleus in the basal ganglia of the brainBrain-derived neurotrophic factorProtein found in humansOrbitofrontal cortexRegion of the prefrontal cortex of the brainVentral tegmental areaGroup of neurons on the floor of the midbrainSlow-wave sleepPeriod of sleep in humans and other animalsVascular endothelial growth factorProtein involved in blood vessel growth