Parallelizing knowledge mining in a cognitive agent for autonomous decision making

Atahary, Tanvir; Taha, Tarek M.; Douglass, Scott

doi:10.1109/sai.2017.8252223

Cited by 7 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The parallel version of that path-based forward checking algorithm was examined on 128 compute nodes at the Ohio Supercomputing Center and achieved 200 times speedup compared to the serial version [11]. A solution ranking capable CDO solver [27] was developed, which was able to rank its solution using various optimization functions. This utilized the forward checking-based algorithm to generate all solutions on a CPU, and these solutions were then ranked using an algorithm running on a GPU.…”

Section: A High Performance Computing Cdo Solving Approachesmentioning

confidence: 99%

Q-Learning Based Cognitive Domain Ontology Representation and Solving on Low Power Computing Platforms

Rahman,

Atahary,

Yakopcic

et al. 2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

Section: A High Performance Computing Cdo Solving Approachesmentioning

confidence: 99%

Q-Learning Based Cognitive Domain Ontology Representation and Solving on Low Power Computing Platforms

Rahman,

Atahary,

Yakopcic

et al. 2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…The work in this paper discusses the implementation of a particular problem that is often tasked to the CDO: M by N asset allocation [12]. In this case we assume that M tasks are present in an assignment description, and N vehicles are available to resolve each task.…”

Section: The M By N Asset Allocation Problemmentioning

confidence: 99%

“…One way to implement these decision making systems in hardware is to use GPUs to execute the instructions which generate the possible outcomes [12]. The problem with this approach is that the asset allocation problem can have an extremely large number of possible outcomes, and checking all of them with a GPU takes an unrealistic amount of time when optimized assignments are needed quickly.…”

Section: The M By N Asset Allocation Problemmentioning

confidence: 99%

“…The studied in this work were executed via remote login to a physical Loihi system. While alternative algorithms for asset allocation have been proposed [27][28][29][30][31] that do not involve an exhaustive search [11][12], we are not aware of any spiking neural network solutions for asset allocation besides [23]. Furthermore, since the recent release of the Loihi processor, very few studies that have utilized the system have been published [24][25][26].…”

Section: Introductionmentioning

confidence: 99%

“…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 have combined complex event processing and cognitive modeling in a cognitively enhanced complex event processing (CECEP) architecture [7][8][9][10][11][12]. The high-performance complex event processing technology at the core of the CECEP architecture distinguishes it from other cognitive modeling frameworks and architectures.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

High Speed Cognitive Domain Ontologies for Asset Allocation Using Loihi Spiking Neurons

Yakopcic

Rahman

Atahary

et al. 2019

2019 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

Cognitive agents are typically utilized in autonomous systems for automated decision making. These systems interact at real time with their environment and are generally heavily power constrained. Thus, there is a strong need for a real time agent running on a low power platform. The agent examined is the Cognitively Enhanced Complex Event Processing (CECEP) architecture. This is an autonomous decision support tool that reasons like humans and enables enhanced agent-based decision-making. It has applications in a large variety of domains including autonomous systems, operations research, intelligence analysis, and data mining. One of the key components of CECEP is the mining of knowledge from a repository described as a Cognitive Domain Ontology (CDO). One problem that is often tasked to CDOs is asset allocation. Given the number of possible solutions in this allocation problem, determining the optimal solution via CDO can be very time consuming. In this work we show that a grid of isolated spiking neurons is capable of generating solutions to this problem very quickly, although some degree of approximation is required to achieve the speedup. However, the approximate spiking approach presented in this work was able to complete all allocation simulations with greater than 99.9% accuracy. To show the feasibility of low power implementation, this algorithm was executed using the Intel Loihi manycore neuromorphic processor. Given the vast increase in speed (greater than 1000 times in larger allocation problems), as well as the reduction in computational requirements, the presented algorithm is ideal for moving asset allocation to low power, portable, embedded hardware.

show abstract

Cognitive Domain Ontologies Based on Loihi Spiking Neurons Implemented Using a Confabulation Inspired Network

Yakopcic

Freeman

Taha

et al. 2019

2019 IEEE Cognitive Communications for Aerospace Applications Workshop (CCAAW)

View full text Add to dashboard Cite

Parallelizing knowledge mining in a cognitive agent for autonomous decision making

Cited by 7 publications

References 20 publications

Q-Learning Based Cognitive Domain Ontology Representation and Solving on Low Power Computing Platforms

Q-Learning Based Cognitive Domain Ontology Representation and Solving on Low Power Computing Platforms

High Speed Cognitive Domain Ontologies for Asset Allocation Using Loihi Spiking Neurons

Cognitive Domain Ontologies Based on Loihi Spiking Neurons Implemented Using a Confabulation Inspired Network

Contact Info

Product

Resources

About