Dropout (MNIST)
University of TorontoCharacter recognition (OCR)
Developed by University of Toronto in 2012, Dropout (MNIST) is a Character recognition (OCR) model with 5594010.0 parameters.
About Dropout (MNIST)
Deep neural nets with a large number of parameters are very powerful machine learning systems. However, overfitting is a serious problem in such networks. Large networks are also slow to use, making it difficult to deal with overfitting by combining
Details
- Provider
- University of Toronto
- Task
- Character recognition (OCR)
- Parameters
- 5594010.0
- Released
- 2012-06-03
- Open weights
- No