This repository is a fork from pnnl/DeepDataProfiler
The Deep Data Profiler library provides tools for analyzing the internal decision structure of a deep neural network within the context of a specific dataset. The library was inspired by the work of Qiu, et al. in Adversarial Defense Through Network Profiling Based Path Extraction (2019), arXiv:1904.08089.
The current version is preliminary. We are actively testing and would be grateful for comments and suggestions. Expect changes in both class names and methods as many of the requirements demanded of the library are worked out.
For questions and comments you may contact the developers directly at:
[email protected]
The research described in this paper is part of the Mathematics of Artificial Reasoning in Science (MARS) Initiative at Pacific Northwest National Laboratory (PNNL). It was conducted under the Laboratory Directed Research and Development Program at PNNL, a multiprogram national laboratory operated by Battelle for the U.S. Department of Energy.
Neither the United States Government nor the United States Department of Energy, nor Battelle, nor any of their employees, nor any jurisdiction or organization that has cooperated in the development of these materials, makes any warranty, express or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness or any information, apparatus, product, software, or process disclosed, or represents that its use would not infringe privately owned rights. Reference herein to any specific commercial product, process, or service by trade name, trademark, manufacturer, or otherwise does not necessarily constitute or imply its endorsement, recommendation, or favoring by the United States Government or any agency thereof, or Battelle Memorial Institute. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof.
PACIFIC NORTHWEST NATIONAL LABORATORY
operated by
BATTELLE
for the
UNITED STATES DEPARTMENT OF ENERGY
under Contract DE-AC05-76RL01830
Released under the 3-Clause BSD license (see License.rst)