Machine Learning Projects for Mobile Applications

Approaches in transfer learning

Lets look into different approaches to transfer learning. There could be different names given to the approaches but the concept remains the same:

1. Use a pre-trained model: There are a lot of pre-trained models out there to satisfy your basic deep learning research. In this book, we have used a lot of pre-trained models from where we derive our results.
2. Train a model for reuse: Assume you wants to solve problem A but you don't have enough data to achieve the results. To solve the issue, we have another problem B where we have enough amount of data. In that case, we can develop a model for problem B and use the model as a starting point for problem A. If we need to reuse all the layers or only a few layers is ...