The power of Transfer Learning

Transfer Learning is a technique in machine learning that focuses on storing knowledge gained from one task and applying it to a different but related task altogether. E.g., the knowledge gained while learning to recognize cars could apply when trying to recognize trucks.

How does that work? Remember that the earlier layers of a deel learning model learn simple shapes. Later layers identify more complex visual patterns. And the very last layers make predictions. So most layers from a pre-trained model are useful in new applications because most computer vision problems involve similar low level visual patterns. A pre-trained Convolutional Neural Network is nothing but a feature extractor — one that extracts a rich set of disciminating features, and Transfer Learning is the ability to use this pre-trained model (for instance a pre-trained ResNet model) as a way to learn patterns from data it was not originally trained on. The ResNet model has many layers. We keep all the layers and just remove the last layer that was used to make predictions. The features extracted previously can be “reused” for other classification tasks.

Transfer Learning is especially used when we don’t have a lot of data to begin with.

Related posts:

Before you purchase residential real estate in Singapore, you might want to find out a little bit more before you sign on the dotted line. In the past couple of years, the Singapore real estate scene…

RSA Conference 2019 is just around the corner. If you are crossing thousands of miles to attend RSA looking to network , build new contacts, and learning opportunities, I can safely assume you plan…

Some think that if you want a job done well then DIY (Do it yourself) is the way ahead. Well that may be true in some cases. But is the DIY policy effective for recruitment? To do things yourself…