Underfitting in a Neural Network
- Underfitting is opposite of overfitting
- The model will not even be able to classify on the data on which it is trained
- Training loss is very high
- Training accuracy is very low
Techniques to reduce underfitting
- 1 ) Increasing the complexity of our model
- like by increasing number of layers
- like increasing number of neurons
- 2) Add more features to the dataset in our training set
- 3) Reducing dropouts
Last modified: Monday, 11 January 2021, 12:21 AM