Deep Transfer Learning (DTL)
DTL emerged as an new paradigm in machine learning in which, a machine is trained using deep models on a source problem, and then transfer learning to solve a target problem. DTL is an alternative to transfer learning with shallow architectures (See Bengio, 2013), in which one specifies a model to several hidden levels of non-linear operations and then estimates the parameters via the likelihood principle. The advantage of DTL is that it offers a far greater flexibility in extracting high-level features and transferring it from a source to a target problem.
