CNN Committee (MNIST)
IDSIAImage classification
Developed by IDSIA in 2011, CNN Committee (MNIST) is a image classification model with 120620.0 parameters.
About CNN Committee (MNIST)
In 2010, after many years of stagnation, the MNIST handwriting recognition benchmark record dropped from 0.40% error rate to 0.35%. Here we report 0.27% for a committee of seven deep CNNs trained on graphics cards, narrowing the gap to human performa
Details
- Provider
- IDSIA
- Task
- Image classification
- Parameters
- 120620.0
- Released
- 2011-09-18
- Open weights
- No