This $174,922 National Science Foundation project grant supports research at the Illinois Institute of Technology to develop immune system-inspired techniques for improving the robustness of neural networks. Funded under the Computer and Information Science and Engineering program, the two-year award aims to incorporate key principles from the immune system into neural network design. Specifically, the grantee will develop an immune-inspired population-point hybrid optimization approach, consider neural network learning from an immune consensus perspective, and allow networks to adapt to unforeseen attacks through lifelong learning and knowledge distillation. By infusing components of the robust immune system into artificial intelligence models, this research seeks to address vulnerabilities in neural networks and enable more resilient machine learning with applications in fields like healthcare and autonomous vehicles.
Mod # | Description | Reason For Modification | Federal Obligation (Click to sort descending) | Date (Click to sort ascending) |
|---|---|---|---|---|
| Not listed | $174.9k | 2/10/23 |