The Transfer Learning technique is very useful because:
Using a well-trained model which performs really great for task A, we can develop a model which performs elegantly for task B, though we have fewer data available for task B
There are fewer parameters to be trained (only last layer/layers) and thus less training time,
There is less demand for heavy computational resources like GPU, TPU (but still depends on the data available for task B).
Taking you to the next exercise in seconds...
Want to create exercises like this yourself? Click here.
No hints are availble for this assesment
Answer is not availble for this assesment
Loading comments...