Hands-On Transfer Learning with Python

Transfer learning methodologies

Deep learning has made considerable progress in recent years and the results are amazing. But the training time and the amount of data required for such deep learning systems is orders of magnitudes more than traditional ML systems.

There are various deep learning networks with state-of-the-art performance (sometimes as good or even better than human performance) that have been developed and tested across domains such as computer vision and natural language processing (NLP). In most cases, teams/people share the details of these networks for others to use (some of the popular ones have been shared in Chapter 3, Understanding Deep Learning Architectures). These pretrained networks/models form the basis of transfer ...