[go: up one dir, main page]
Scribd
Upload
24 views6 pages

4 Overfitting

Uploaded by

binduann
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
24 views6 pages

4 Overfitting

Uploaded by

binduann
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 6

OVERFITTIN

G
Overfitting refers to the phenomenon
where a neural network models the
training data very well but fails when it
sees new data from the same problem
domain.
Overfitting is caused by noise in the
training data that the neural network picks
up during training and learns it as an
underlying concept of the data.
Common regularization techniques:
1. Dropout (randomly shutdowns some unit
to prevents co-adaptation)
2. Drop connect ( randomly drop
connections)
 Bias- Training data error
 Variance- test data error
 Underfitting- model is not learning enough
(high bias)
 Overfitting-model is not flexible enough
(high variance)
 Good balance – balance btn overfitting and
underfitting (regularize the model)
12/10/2 6
024

You might also like