3 years ago

Category: Data

https://twitter.com/flippedcoding The approach to taking an existing model and applying it to a different problem is called transfer learning. Now you have this model that has been going through the training process with a specific dataset and you need to adapt the model to handle this new problem.

Your existing model has already learned how to handle a few images, so you don’t have to restart the entire training process.

Here are a few reasons we would want to apply transfer learning to a pre-trained model.

Taking an NLP pre-trained model could shorten the time it takes to build an accurate model.