Let's say that we want to train a model on a task that doesn't have readily available labeled training data like ImageNet does. Labeling training samples could be expensive, time-consuming, and error-prone. So, what does a humble engineer do when they want to solve a real ML problem with limited resources? Enter Transfer Learning (TL).
TL is the process of applying an existing trained ML model to a new, but related, problem. For example, we can take a network trained on ImageNet and repurpose it to classify grocery store items. Alternatively, we could use a driving simulator game to train a neural network to drive a simulated car and then use the network to drive a real car (but don't try this at home!). TL is a general ML concept that's applicable to all ML algorithms, but in this context, we'll talk about CNNs. Here&apos...
