Cignal Checkpoint, part of the Cignal High-Performance Computing (HPC) Stack, is our full-featured simulation environment that enables flexible and adaptable training for AI/ML models, especially in challenging X-ray/CT inspection and detection scenarios.
Checkpoint creates and visualizes datasets by packing/filling different objects, dynamically editing properties of materials, and exporting data in numerous formats, such as NumPy or DICOS - activities that may come in handy in security inspection and nondestructive testing environments.
New model training paradigms, such as reinforcement learning, are supported by Checkpoint, and it can be used to identify potential weaknesses in a given model. As a bonus, Checkpoint also can help to make AI models more explainable.
If you'd like to learn more about Cignal Checkpoint's features and benefits, please contact us at innovation@cignal.co
Research reported in this publication was supported by the Department of Homeland Security, Science and Technology Directorate under Award Number 70RSAT21T00000010. The content is solely the responsibility of the authors and does not necessarily represent the official views of the Department of Homeland Security.