Deep Learning: Integrating Domain Knowledge and Interpreting the Network Decisions

The major goal of this project is to develop a principled approach to integrate domain knowledge in the lifecycle of deep learning and effectively reduce the model complexity and thereby training robust and accurate deep models using the limited amount of training data available. The proposed approach includes three major tasks: Integrate data knowledge from auxiliary data sources to revise the formulation of deep learning, in the form of knowledge-defined structural regularization or constraints on the parametric space; Integrate model knowledge, where we exploit the decision surfaces from simpler models on the same task to guide the learning of the deep model, which effectively reduces the model complexity; Integrate optimizer knowledge, which seeks to improve the optimization procedure of the training of deep models. By identifying similar learning tasks and observing their gradient trajectories, the optimizer itself can be trained to provide faster convergence and also avoid poor local optimal solutions; A byproduct of integrating domain knowledge will be to impart interpretability or explain-ability to the network decision making, a much desired capability which is currently lacking.