A Bio-inspired Hyperdimensional Intelligent Sensing and Information Processing
Abstract
Defense applications often analyze collected sensor data using machine learning algorithms. Unfortunately, the existing sensing systems lack intelligence about the target and naively generate large-scale data, making communication and computation significantly costly. However, in many cases, the data generated by sensors only contain useful information for a small portion of the sensor activity. For example, machine learning algorithms continuously process the visual sensors used for environmental/security monitoring to detect sensitive activities. Still, these sensors only carry out useful information for a short time. On the other hand, biological sensors intelligently generate orders of magnitude less amount of data. In this project, we will develop brain-inspired learning algorithms that provide real-time feedback to sensors to ensure they only generate data needed for learning purposes. This feedback alsoenables an attention mechanism that makes sensors aware of the target task,enabling situational awareness. We also develop a novel framework that tightly integrates with a sensing circuit and brain-inspired algorithms to dynamically control the sensor functionality in a fully self-supervised manner. Our approach is expected to provide up to four orders of magnitude data reduction from sensors. The results from this research will broadly impact many sensors used in naval applications, including national security, energy management, infrastructure, and autonomous systems.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Jan 24, 2024
- Source ID
- N000142412084
Entities
People
- Mohsen Imani
Organizations
- Office of Naval Research
- United States Navy
- University of California, Irvine