Figure - available from: The Journal of Supercomputing
This content is subject to copyright. Terms and conditions apply.
Source publication
The cognitively enhanced complex event processing (CECEP) architecture being developed at the US Air Force is an autonomous decision support tool that reasons and learns like humans and enables enhanced agent-based decision making. It has applications in both military and civilian domains. One of the most computationally challenging aspects of CECE...
Citations
... Screamer+ [23] is a LISP based non-deterministic programming environment which was used to solve CDOs. A modified version of that exhaustive depth-first search algorithm [24] implemented with a NVIDIA graphics processor (Tesla C2070) achieved 100 times speedup over a Xeon processor implementation and almost 8 times speedup over a Xeon Phi processor implementation. Forward checking prunes the solution search space based on the constrains provided and as such is more efficient than exhaustive depth first search brute force approaches. ...
Cognitive agents make systems autonomous through the process of decision automation by mining an existing knowledge repository at run time. These processes can often be highly compute intensive, and would thus run slowly on the low-power computing platforms typically seen in autonomous systems. This paper examines how knowledge be represented in a Q-table and proposes a novel fast algorithm to mine that knowledge based on constraints. We evaluate this approach for the knowledge mining process of a specific agent: Cognitively Enhanced Complex Event Processing (CECEP). Within CECEP, knowledge is represented using Cognitive Domain Ontologies (CDO), and is mined using situational inputs and constraints. This is a novel approach to store information and is able to accommodate CDOs with millions of solutions. To show that the approach can run on low power hardware in real-time, this algorithm was executed on two low-power minicomputing platforms - Intel’s NUC and Asus’s Tinker Board. At present, no other optimized CDO solvers can generate solutions on these platforms. The algorithm generated the same amount of solutions as a GPU-enabled optimized path-based forward checking CDO solver, while consuming around 7.7 and 5.15 times less energy on the NUC and Tinker Board respectively.
... Multiple cognitive architectures have been developed over the years [1][2][3][4][5][6], among which SOAR [3] and ACT-R [4][5][6] are two of the most widely explored. Cognitive scientists in the Air Force Research Laboratory (AFRL) have combined complex event processing and cognitive modeling in a cognitively enhanced complex event processing (CECEP) architecture [7][8][9][10]. The high-performance complex event processing technology at the core of the CECEP architecture distinguishes it from other cognitive modeling frameworks and architectures. ...
... It is well suited to the challenges of developing autonomous decision support tools that reason and learn like humans. The CECEP framework [7] consists of a coordinated set of net-centric event processing components each of which provides a unique information/ knowledge processing capability. Event processing components in the CECEP architecture that process declarative, procedural and domain knowledge distinguish it from all other complex event processing frameworks by incorporating "cognitive enhancements" based on cognitive architectures. ...
... Object relationships include information about how a domain is structured (i.e., how objects are decomposed into parts) as well as which combinations of objects and their properties are valid instances of the domain (i.e., make sense). Domain knowledge is represented in CDOs, which are processed by a constraint satisfaction framework [7]. ...
Cognitive agents are typically utilized in autonomous systems for automated decision making. With the widespread use of autonomous systems in complex environments, the need for real-time cognitive agents is essential. Cognitive agents are more capable when they are able to process larger amounts of information to make more informed and intelligent decisions. The solution search space for cognitive agents increases exponentially with large volumes of varied data. In this paper, we present the parallelization of the knowledge-mining component of a cognitive agent that can be programmed to reason like humans. This study examined a novel high-performance path-based forward checking algorithm on 128 compute nodes at the Ohio Supercomputing Center (768 cores) to achieve a speedup of over 200 times compared to a serial implementation of our algorithm. The serial implementation is around 10–25 times faster than a conventional Java-based constraint solver at generating the first solution.
... Backtracking based search algorithms are the most common search approach for solving constraint satisfaction problems. CDOs have traditionally been solved with Java or C++ based solvers using multi-core and many core architectures [16][17]. ...
