An example of this concept exists in image classification. If someone wants to classify kinds of clouds it can be very difficult to compile enough data to train a model from scratch. However, models such as ImageNet have already been trained on classifying a lot more and different kinds of images so under the assumption that the earlier layers in the model hold some fundamental information about understanding images then transfer learning can be used. Then, we need to replace the output layer of the pre-trained model with a new output layer(s) that match the number of classes of the new output variable and then train the model.