Visualizing complex feature interactions and feature sharing in genomic deep neural networks.

Journal: BMC bioinformatics
Published Date:

Abstract

BACKGROUND: Visualization tools for deep learning models typically focus on discovering key input features without considering how such low level features are combined in intermediate layers to make decisions. Moreover, many of these methods examine a network's response to specific input examples that may be insufficient to reveal the complexity of model decision making.

Authors

  • Ge Liu
    Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02142, USA.
  • Haoyang Zeng
    Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02142, USA.
  • David K Gifford
    Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02142, USA.