- Number of parameters can be altered depending on the difference between test score and training score. Also, keeping in mind the complexity(non-linearity) of the data.
- Dropout neurons: adding dropout neurons to reduce overfitting.
- Regularization: L1 and L2 regularization.
Convolutional Neural Network Transfer Learning
2 views (last 30 days)
I am working on a handwritten character recognition project with CNN and I trained my CNN with MNIST dataset. Since the handwriting are vary from person to person, so I am looking for some kind of "transfer learning" that allows me to perform incremental training on my trained CNN ( trained with MNIST dataset ) with the handwriting from others.
Hope this question is understable :D
Puru Kathuria on 11 May 2021
While training the network, you can keep in mind the goal to generalize the network and reduce overfitting. The concept of learning from some data and correctly applying the gained knowledge on other data is generalization. There are certain aspects that control the degree of overfitting and generalization.
After you have trained the network, you can successfully use that same network to perform prediction on other handwritten digits dataset. This process will be termed as transfer learning.