Deep Domain Adaptation.

Deep learning architectures have brought impressive advances to the state-of-the-art across a wide variety of machine-learning tasks and applications. At the moment, however, these performance come only when a large amount of labeled training data is available. One of the main problems of these models is that in many real world applications of machine learning, the distribution of the training data (on which the machine learning model is trained) is different from the distribu- tion of the test data (where the learnt model is actually deployed). This is known as the problem of Domain Adaptation. The goal of this homework is to implement a Domain Adaptation algorithm based on AlexNet, a network already used in the last homework.