Anil Jain and Jiayu Zhou awarded ONR grant

Anil Jain, University Distinguished Professor of Computer Science and Engineering, and Jiayu Zhou, Assistant Professor of Computer Science and Engineering have been awarded an ONR grant titled “Deep Learning: Integrating Domain Knowledge and Interpretability”.

Abstract:

 

The proliferation of big and complex data has led to new developments and widespread use of machine learning models, especially the deep models. Their model complexity and expressiveness result in non-linear boundaries. This has lead to the huge success of deep networks and their adoption in areas such as computer vision and natural language processing. One major challenge of deep learning is the requirement of large training data to learn the very large numbers of parameters. However, generating enough training data for deep learning models may not be feasible in many applications due to its cost, large collection time, and availability of only small amounts of data in some domains. Fortunately, in many learning problems, various types of domain knowledge can be explored and exploited to overcome the challenges due to model complexity and overfitting. In this project, we propose 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.