1 Answers

Prakash nidhi Verma
Prakash nidhi Verma

In machine learning when a statistical model has error, noiseless data, uncleared data in that's situation ‘overfitting’ occurs. When a model is excessively complex, overfitting is normally occur because of having too many parameters with respect to data types In overfit models exhibits having very poor performance. 

The overfitting possibility exists as the criteria used for training the model is not the same as  that's efficiency.  lot of data overfitting can be avoided by using this, overfitting like you have a small dataset, and  you try to learn from it. But if you have a small database and you are forced to come with a model  based on problem. In such case you can use a technique known as cross validation. dataset splits into two section in this method. 

- Testing datasets

- Training datasets

the testing dataset will only test the model but in training dataset the datapoints will come up with the model.