In this tutorial, we will cover the process of transfer learning.

Transfer learning is a machine learning technique in which a network that has been trained to perform a specific task is being reused (re-purposed) as a starting point for another similar task.

Transfer learning is widely used since starting from a pre-trained models can dramatically reduce the computational time required if training is performed from scratch.

In transfer learning, a base (reference) Artificial Neural Network on a base dataset and function is being trained. Then, this trained network weights are then re-purposed in a second ANN to be trained on a new dataset and function.

Transfer learning works great if the features are general, such that trained weights can effectively re-purposed.

Intelligence is being transferred from the base network to the newly target network.

I hope you enjoyed this tutorial.

Thanks and Happy Learning!