This NSF-funded Project Grant award, with a total funding amount of $250,000, supports a collaborative research effort to develop formal methods for the synthesis and verification of in-memory computing systems. The key objectives are to create formal methods for synthesizing neural networks in computer memory and proving their correctness, as well as verifying neural networks accelerated using analog in-memory computing. The project aims to enable the deployment of robust AI models on emerging in-memory hardware technologies, reduce power consumption during neural network training, and enhance the reliability of neural networks on in-memory circuits. This work is expected to advance the fields of in-memory computing, formal methods, and artificial intelligence through cross-disciplinary collaboration between experts in areas such as formal methods, machine learning, computer-aided design, and hardware fabrication. The project is led by Florida International University and runs from November 1, 2023 to August 31, 2027.
Mod # | Description | Reason For Modification | Federal Obligation (Click to sort descending) | Date (Click to sort ascending) |
|---|---|---|---|---|
| Not listed | $250.0k | 12/8/23 |