Transfer learning, is a research problem in machine learning that focuses on storing knowledge gained while solving one problem and applying it to a different but related problem.
Why Transfer Learning?
In practice a very few people train a Convolution network from scratch (random initialisation) because it is rare to get enough dataset. So, using pre-trained network weights as initialisations or a fixed feature extractor helps in solving most of the problems in hand.
Very Deep Networks are expensive to train. The most complex models take weeks to train using hundreds of machines equipped with expensive GPUs.
Determining the topology/flavour/training method/hyper parameters for deep learning is a black art with not much theory to guide you.
How Transfer Learning helps ?
When you look at what these Deep Learning networks learn, they try to detect edges in the earlier layers, Shapes in the middle layer and some high level data specific features in the later layers. These trained networks are generally helpful in solving other computer vision problems. Lets have a look at how to do transfer learning using Keras and various cases in Transfer learning.
Transfer Learning`
Reviewed by Anthony
on
July 13, 2021
Rating: 5
No comments
If you have any doubts, Please let me know