As discussed in Chapter 3, Understanding Deep Learning Architectures deep learning systems are layered architectures that learn different features at different layers. These layers are then finally connected to a last layer (usually a fully connected layer, in the case of classification) to get the final output. This layered architecture allows us to utilize a pretrained network (such as Inception V3 or VGG) without its final layer as a fixed feature-extractor for other tasks. The following diagram represents deep transfer based on feature-extraction:

For instance, if we utilize AlexNet without its final classification layer, it will help us transform images from a new domain task into a 4,096-dimensional vector based on its hidden states, thus enabling us to extract features from a new domain task, utilizing the knowledge from a source-domain task. This is one of the most widely utilized methods of performing transfer learning using deep neural networks.