Cortical Processor
Abstract
Capturing complex spatial and temporal structure in high-bandwidth, noisy, ambiguous data streams to meet DoD's needs cannot be achieved even by state-of-the-art signal/image analysis systems. However, there is a processing structure in nature, the mammalian neocortex, that efficiently captures spatial and temporal structure and routinely solves the most difficult recognition problems in real-time and is a general purpose structure for a range of sensor data processing and motor control execution. The Cortical Processor program will leverage simplified models of known cortical operation to develop a new processor architecture that is optimized for running a family of algorithms known as Hierarchical Temporal Memory (HTM), providing new levels of performance and capabilities to a broad range of data recognition problems. HTM models map well to simple, massively parallel, signal processor arrays and a cortical processor leveraging advances in dense memory structures on a Complementary Metal-Oxide-Semiconductor (CMOS) chip running at a few watts can perform orders of magnitude larger tasks than an HTM system simulated by commercial efforts on large data-center clusters. With certain specialized circuits, several orders of magnitude improvement in throughput and efficiency will be possible with the cortical processor, enabling a wide range of powerful, ultra-low power, embedded applications. Executing large HTM models on modest-sized embedded platforms will transform the DoD's ability to convert huge quantities of data into actionable information. By augmenting tactical sensor systems on the battlefield with the new functionalities of predictive analyses and anomaly detection, this technology will have a major impact on the abilities of autonomous vehicles, robots, and UAVs. The Cortical Processor will adapt to changing environments while reducing the need for a man in-the-loop, providing entirely new capabilities that cannot be achieved with today's commercial hardware. This technology will enable more complex missions, particularly for surveillance systems and portable analytics and knowledge extraction from vision sensors and multi-model integration for the DoD and intelligence communities. Basic research for the program is budgeted in PE 0601101E, Project CCS-02.
Document Details
- Document Type
- Accomplishment
- Publication Date
- Oct 01, 2015
- Source ID
- 55471d57b8a57084289e67f71e3955d7