Complexity Management Hardware*
Abstract
*Formerly Cortical Processor The battlefield of the future will certainly have more data generators and sensors that define the information required to execute appropriately. With networked sensors, the variety and complexity of the information streams will be even further extended. This project will explore silicon designs which help alleviate the complexity inherent in next generation systems. These systems will have increasingly large data sets generated by their own multidomain sensors (such as RF and Electro-Optical/Infrared (EO/IR) payloads) as well as new inputs from external sensors that may or may not have been planned for initially. With current programming approaches, there are laborious coding requirements which need to account for new data streams. However, the context provided by these data sets is ever changing, and it is imperative for the integrated electronics to adapt to new information without a prolonged programming cycle. Providing contextual cues for processing of data streams will alleviate the fusion challenges that are currently faced, and which stress networked battlefield systems. As opposed to the intuition and future-proofing that is required at the programming stage of a current system, the silicon circuit of the future will be able to use contextual cues to adapt accordingly to new information as it is provided. The fundamental aspects of this program will look at various algorithms to explore the ability to use context to adapt to new information. This will start with exploration of the ability to automatically recognize information within streams of data, and then to extract context from the dataset. This will extend to exploiting that context to further refine the processing of an orthogonal data set. Applied research for the program is budgeted in PE 0602303E, Project IT-02.
Document Details
- Document Type
- Accomplishment
- Publication Date
- Oct 01, 2016
- Source ID
- f67481768e7f609c0b1bd6359816249b