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

Alex Beigh; Chris Yakopcic; Nayim Rahman; Scott Douglass; Tanvir Atahary; Tarek M. Taha

arxiv: 1906.12338 · v1 · pith:LWMJVPCCnew · submitted 2019-06-28 · 💻 cs.NE · eess.SP

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

Chris Yakopcic , Nayim Rahman , Tanvir Atahary , Tarek M. Taha , Alex Beigh , Scott Douglass This is my paper

Pith reviewed 2026-05-25 13:09 UTC · model grok-4.3

classification 💻 cs.NE eess.SP

keywords spiking neuronsasset allocationcognitive domain ontologyneuromorphic hardwareautonomous systemsdecision supportevent processing

0 comments

The pith

A grid of isolated spiking neurons solves asset allocation problems from cognitive domain ontologies over 1000 times faster while keeping more than 99.9 percent accuracy.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper shows that a grid of isolated spiking neurons can perform the knowledge-mining step inside cognitive domain ontologies for asset allocation. This produces solutions with greater than 99.9 percent accuracy and delivers speedups exceeding 1000 times on larger problems. The authors run the method on neuromorphic hardware to establish that it fits low-power embedded platforms. The work targets real-time use in power-constrained autonomous decision systems where exact ontology methods are too slow.

Core claim

The paper claims that an approximate spiking approach using a grid of isolated spiking neurons completes all allocation simulations with greater than 99.9 percent accuracy and achieves a vast increase in speed, greater than 1000 times in larger allocation problems, making the algorithm ideal for low power, portable, embedded hardware.

What carries the argument

A grid of isolated spiking neurons that encodes the knowledge-mining step of a cognitive domain ontology and generates approximate allocation solutions.

If this is right

Asset allocation moves from slow exact methods to real-time operation on low-power embedded hardware.
Larger problems receive the greatest relative speedup while accuracy stays high.
The approach reduces overall computational requirements enough for portable autonomous systems.
The same spiking grid can support decision tasks across domains that use cognitive domain ontologies.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The encoding technique could be tested on other ontology-based reasoning steps beyond allocation to check for similar speed gains.
Hardware-level power measurements on the neuromorphic chip would quantify energy savings against conventional processors.
If the neuron parameters prove robust, the method might generalize to related optimization tasks encoded in similar ontologies.

Load-bearing premise

The isolated spiking neuron grid faithfully encodes the knowledge-mining step of a cognitive domain ontology without introducing systematic bias that would degrade downstream decision quality in real deployments.

What would settle it

A direct comparison of allocation outputs from the spiking grid against an exact solver across a range of problem sizes, checking whether any problem class shows accuracy below 99.9 percent or consistent selection bias.

Figures

Figures reproduced from arXiv: 1906.12338 by Alex Beigh, Chris Yakopcic, Nayim Rahman, Scott Douglass, Tanvir Atahary, Tarek M. Taha.

**Figure 2.** Figure 2: Block diagram for the spiking neuron based asset allocation system [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗

**Figure 3.** Figure 3: Connection diagram for the proposed isolated neuron matrix. [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗

**Figure 5.** Figure 5: Block diagram displaying connection diagram, weights, and neurons [PITH_FULL_IMAGE:figures/full_fig_p005_5.png] view at source ↗

**Figure 6.** Figure 6: Plots displaying the result of a 4 × 4 task allocation executed on the Loihi [PITH_FULL_IMAGE:figures/full_fig_p006_6.png] view at source ↗

read the original abstract

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.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

This paper delivers a Loihi hardware run of spiking neurons for CDO asset allocation with claimed 99.9% accuracy and large speedups, but supplies almost no methodological detail on baselines, parameter choice, or error measurement.

read the letter

The main thing to know is that the authors map asset allocation from a cognitive domain ontology onto a grid of isolated spiking neurons, run it on Loihi, and report over 99.9 percent accuracy plus speedups above 1000 times for bigger instances. That hardware measurement is the concrete new piece; earlier spiking-optimization work exists, but executing this specific CECEP task on actual neuromorphic silicon is a step that was not in the cited literature. It does a serviceable job showing that approximation via spiking neurons can cut power and latency for embedded decision agents, which matters for the low-power autonomous-systems angle they emphasize. The numbers are presented as direct hardware observations rather than fitted models, so they stand as empirical evidence of feasibility. The soft spots sit in the missing validation steps. No baseline solver is described, no dataset sizes or error-bar information appears, and there is no account of how neuron weights, thresholds, or firing rates were selected or checked against the ontology structure. Without that mapping procedure or a sensitivity check, it is difficult to know whether the reported accuracy reflects faithful preservation of decision quality or simply good performance on the chosen test cases. The isolated-neuron constraint also leaves open whether higher-order ontology relations can be captured without inter-neuron dynamics. This work is mainly for people already inside neuromorphic hardware or cognitive-agent implementations; readers outside that niche will see limited value until the method details are filled in. It deserves peer review because the hardware results give referees something tangible to examine for reproducibility and practical limits, even though the paper will likely need substantial revision on the methods side before publication.

Referee Report

3 major / 1 minor

Summary. The manuscript claims that a grid of isolated spiking neurons implemented on the Intel Loihi neuromorphic processor can solve asset allocation problems drawn from Cognitive Domain Ontologies (CDOs) within the CECEP architecture. It reports that this approximate method completes all tested simulations with greater than 99.9% accuracy while delivering speedups exceeding 1000 times for larger problems, thereby enabling low-power, real-time operation on embedded hardware.

Significance. If the performance claims are substantiated, the work would be significant for demonstrating neuromorphic hardware acceleration of ontology-based cognitive decision support. The explicit execution on Loihi hardware is a strength that supports reproducibility of the hardware results and directly addresses power constraints in autonomous systems.

major comments (3)

Abstract: The claim that the approximate spiking approach completed all allocation simulations with greater than 99.9% accuracy supplies no baseline algorithm, dataset sizes, error bars, or description of how approximation error was measured against the non-spiking CDO, rendering the central accuracy result unverifiable from the given text.
Abstract: The mapping of ontology relations to spiking-neuron weights, thresholds, and firing rates is not described, nor is any validation (e.g., sensitivity analysis or equivalence check) provided to confirm that the isolated-neuron grid preserves downstream decision quality without introducing systematic bias.
Abstract: The reported speedup of greater than 1000 times in larger allocation problems is stated without identifying the reference implementation or hardware platform used for comparison, which is required to evaluate the practical significance of the result.

minor comments (1)

The manuscript would benefit from a table or figure that tabulates problem sizes, accuracy, and runtime metrics to make the empirical results easier to assess.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the detailed review and constructive comments on our manuscript. We address each major comment below and will revise the abstract accordingly to improve verifiability while preserving the core claims supported by the full text.

read point-by-point responses

Referee: Abstract: The claim that the approximate spiking approach completed all allocation simulations with greater than 99.9% accuracy supplies no baseline algorithm, dataset sizes, error bars, or description of how approximation error was measured against the non-spiking CDO, rendering the central accuracy result unverifiable from the given text.

Authors: We agree the abstract is too terse on these points. The full manuscript specifies the baseline as the standard non-spiking CDO solver, uses allocation problem sizes from tens to hundreds of assets, and measures error as the percentage of solutions matching the exact CDO output (all cases >99.9%). No error bars appear because accuracy was deterministic across the reported runs. We will revise the abstract to include a short clause identifying the baseline, problem scale, and matching metric. revision: yes
Referee: Abstract: The mapping of ontology relations to spiking-neuron weights, thresholds, and firing rates is not described, nor is any validation (e.g., sensitivity analysis or equivalence check) provided to confirm that the isolated-neuron grid preserves downstream decision quality without introducing systematic bias.

Authors: The abstract omits the mapping details present in the methods section, where CDO relations are encoded as synaptic weights proportional to relation strength, thresholds set to enforce valid allocation constraints, and firing rates tuned for convergence speed. Equivalence is validated by direct output comparison to the non-spiking CDO on the same inputs, showing no systematic bias in the tested cases. We will add one sentence to the abstract summarizing the mapping and the direct-comparison validation. revision: yes
Referee: Abstract: The reported speedup of greater than 1000 times in larger allocation problems is stated without identifying the reference implementation or hardware platform used for comparison, which is required to evaluate the practical significance of the result.

Authors: We accept that the reference must be explicit. The >1000x figure compares Loihi execution time against the same CDO algorithm running as conventional software on a standard multi-core CPU. We will revise the abstract to state the comparison baseline explicitly. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical hardware measurements of spiking-neuron asset allocation on Loihi presented without self-referential derivations or fitted predictions

full rationale

The paper reports measured outcomes (>99.9% accuracy, >1000x speedup) from executing an approximate spiking-neuron implementation of CDO asset allocation on the Loihi processor. No equations, parameter-fitting procedures, or self-citations appear in the abstract or described content that would reduce the accuracy or speedup claims to quantities defined by the authors' own prior work or by construction. The result is framed as an empirical hardware demonstration rather than a derived prediction, satisfying the self-contained criterion with no load-bearing self-definition or renaming steps.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The central claim rests on the unstated premise that a simple grid of isolated spiking neurons can serve as a drop-in surrogate for the knowledge-mining component of a CDO; no free parameters, axioms, or invented entities are enumerated in the abstract.

pith-pipeline@v0.9.0 · 5826 in / 1143 out tokens · 22754 ms · 2026-05-25T13:09:09.550695+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

31 extracted references · 31 canonical work pages · 1 internal anchor

[1]

A survey of cognitive and agent architectures

Wray, Robert, et al. "A survey of cognitive and agent architectures." University of Michigan (1994)

work page 1994
[2]

Integrated cognitive architectures: a survey

Chong, Hui-Qing, Ah-Hwee Tan, and Gee-Wah Ng. "Integrated cognitive architectures: a survey." Artificial Intelligence Review 28.2 (2007): 103- 130

work page 2007
[3]

The Soar cognitive architecture

Laird, John E. The Soar cognitive architecture. MIT Press, 2012

work page 2012
[4]

The Architecture of Cognition’, Harvard University Press, Cambridge, MA

Anderson, John R. "The Architecture of Cognition’, Harvard University Press, Cambridge, MA." (1983)

work page 1983
[5]

Anderson Richard King

Mellon, John R. Anderson Richard King. How can the human mind occur in the physical universe?. Oxford University Press, USA, 2007

work page 2007
[6]

An integrated theory of the mind

J. R. Anderson, Bothell, M.D. Byrne, S. Douglass, C. Lebiere, & Y. Qin, “An integrated theory of the mind”. Psychological Review 111, (4), 2004

work page 2004
[7]

Hardware Accelerated Cognitively Enhanced Complex Event Processing

T. Atahary, T. Taha, S. Douglass, “Hardware Accelerated Cognitively Enhanced Complex Event Processing”, 14th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, July, SNPD 2013

work page 2013
[8]

The power of events: An introduction to complex event processing in distributed enterprise systems

D. Luckham, “The power of events: An introduction to complex event processing in distributed enterprise systems”. Springer Berlin Heidelberg, 2008

work page 2008
[9]

Concurrent knowledge activation calculation in large declarative memories

S. Douglass, C. Myers, “Concurrent knowledge activation calculation in large declarative memories”, Proceedings of the 10th International Conference on Cognitive Modeling, 55–60, 2010

work page 2010
[10]

Esper available: http://esper.codehaus.org/

work page
[11]

Knowledge mining for cognitive agents through path based forward checking,

T. Atahary, T. Taha, F. Webber, amd S. Douglass, “Knowledge mining for cognitive agents through path based forward checking,” 16th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), pp. 1-8, June, 2015

work page 2015
[12]

Parallelizing knowledge mining in a cognitive agent for autonomous decision making,

T. Atahary, T. Taha and S. Douglass, "Parallelizing knowledge mining in a cognitive agent for autonomous decision making," 2017 Computing Conference, London, 2017, pp. 1058-1068

work page 2017
[13]

Cognitive computing building block: A versatile and efficient digital neuron model for neurosynaptic cores,

A. S. Cassidy, P. Merolla, J. V. Arthur, S. K. Esser, B. Jackson, R. Alvarez-Icaza, P. Datta, J. Sawada, T. M. Wong, V. Feldman, A. Amir, D. B.-D. Rubin, F. Akopyan, E. McQuinn, W. P. Risk, and D. S. Modha “Cognitive computing building block: A versatile and efficient digital neuron model for neurosynaptic cores,” International Joint Conference on Neural ...

work page 2013
[14]

Cognitive computing programming paradigm: A Corelet Language for composing networks of neurosynaptic cores,

A. Amir, P. Datta, W. P. Risk, A. S. Cassidy, J. A. Kusnitz, S. K. Esser, A. Andreopoulos, T. M. Wong, M. Flickner, R. Alvarez-Icaza, E. McQuinn, B. Shaw, N. Pass, and D. S. Modha, “Cognitive computing programming paradigm: A Corelet Language for composing networks of neurosynaptic cores,” pp. 1-10, Dallas, TX, August 2013

work page 2013
[15]

Memristor Crossbar Based Multicore Neuromorphic Processors,

T. M. Taha, R. Hasan, and C. Yakopcic, “Memristor Crossbar Based Multicore Neuromorphic Processors,” IEEE International System-on- Chip Conference (SOCC), pp. 383-389, Las Vegas, NV, Sept. 2014

work page 2014
[16]

Flexible Memristor Based Neuromorphic System for Implementing Multi-layer Neural Network Algorithms,

C. Yakopcic, R. Hasan, and T. M. Taha, "Flexible Memristor Based Neuromorphic System for Implementing Multi-layer Neural Network Algorithms," International Journal of Parallel, Emergent and Distributed Systems, vol. 33, no. 4, pp. 408-429, 2018

work page 2018
[17]

Extremely Parallel Memristor Crossbar Architecture for Convolutional Neural Network Implementation,

C. Yakopcic, Z. Alom and T. Taha, “Extremely Parallel Memristor Crossbar Architecture for Convolutional Neural Network Implementation,” IEEE/INNS International Joint Conference on Neural Networks (IJCNN), pp. 1696-1703, Anchorage, AK, May 2017

work page 2017
[18]

Method for ex-situ training in a memristor-based neuromorphic circuit using a robust weight programming method,

C. Yakopcic, T. M. Taha, M. R. McLean, “Method for ex-situ training in a memristor-based neuromorphic circuit using a robust weight programming method,” Electronics Letters, vol. 51, no. 12, pp. 899-900, 2015

work page 2015
[19]

Memristor Crossbar Deep Network Implementation Based on a Convolutional Neural Network,

C. Yakopcic, M. Z. Alom, and T. M. Taha, “Memristor Crossbar Deep Network Implementation Based on a Convolutional Neural Network,” IEEE/INNS International Joint Conference on Neural Networks (IJCNN), pp. 963-970, Vancouver, BC, July 2016

work page 2016
[20]

Cognitive Domain Ontologies in Lookup Tables Stored in a Memristor String Matching Architecture,

N . R a h m a n , C . Y a k o p c i c , T . A t a h a r y , R . H a s a n , T . M . T a h a , a n d S . Douglass, “Cognitive Domain Ontologies in Lookup Tables Stored in a Memristor String Matching Architecture,” 30th annual IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), pp. 1-4, Windsor, Ontario, April 2017

work page 2017
[21]

Cognitive Domain Ontologies in a Memristor Crossbar Architecture,

C. Yakopcic, N. Rahman, T. Atahary, T. M. Taha, and S. Douglass, “Cognitive Domain Ontologies in a Memristor Crossbar Architecture,” IEEE National Aerospace and Electronics Conference (NAECON), pp. 76-83, Dayton, OH, June 2017

work page 2017
[22]

Task Allocation Performance Comparison for Low Power Devices,

N. Rahman, T. Atahary, C. Yakopcic, T. M. Taha, Scott Douglass, “Task Allocation Performance Comparison for Low Power Devices,” IEEE National Aerospace and Electronics Conference (NAECON), pp. 247- 253, Dayton, OH, July, 2018

work page 2018
[23]

High Speed Approximate Cognitive Domain Ontologies for Asset Allocation based on Isolated Spiking Neurons,

C. Yakopcic, T. Atahary, T. M. Taha, A. Beigh, and S. Douglass, “High Speed Approximate Cognitive Domain Ontologies for Asset Allocation based on Isolated Spiking Neurons,” IEEE National Aerospace and Electronics Conference (NAECON), pp. 241-246, Dayton, OH, July, 2018

work page 2018
[24]

Loihi: A Neuromorphic Manycore Processor with On-Chip Learning,

M. Davies, N. Srinivasa, T.-H. Lin, G. Chinya, Y. Cao, S. H. Choday, G. Dimou, P. Joshi, N. Imam, S. Jain, Y. Liao, C.-K. Lin, A. Lines, R. Liu, D. Mathaikutty, S. McCoy, A. Paul, J. Tse, G. Venkataramanan, Y.-H. Weng, A. Wild, Y. Yang, H. Wang, “Loihi: A Neuromorphic Manycore Processor with On-Chip Learning,” IEEE Micro, vol. 38, no. 1, pp. 82- 99, 2018

work page 2018
[25]

Programming Spiking Neural Networks on Intel’s Loihi,

C.-K. Lin, A. Wild, G. N. Chinya, Y. Cao, M. Davies, D. M. Lavery, H. Wang, “Programming Spiking Neural Networks on Intel’s Loihi,” Computer, vol. 51, no. 3, pp. 52-61, 2018

work page 2018
[26]

Benchmarking Keyword Spotting Efficiency on Neuromorphic Hardware

P. Blouw, X. Choo, E. Hunsberger, C. Eliasmith, “Benchmarking Keyword Spotting Efficiency on Neuromorphic Hardware,” arXiv :1812.01739, submitted 4 Dec. 2018

work page internal anchor Pith review Pith/arXiv arXiv 2018
[27]

Methods for task allocation via agent coalition formation

O. Shehory, S. Kraus, “Methods for task allocation via agent coalition formation.” Artificial intelligence 101.1-2 (1998): 165-200

work page 1998
[28]

Multi-task allocation and path planning for cooperating UAVs

J. Bellingham, M. Tillerson, A. Richards, J. P. How, "Multi-task allocation and path planning for cooperating UAVs." Cooperative control: models, applications and algorithms. Springer, Boston, MA,

work page
[29]

C e n t r a l i z e d a n d d i s t r i b u t e d t a s k allocation in multi-robot teams via a stochastic clustering auction

K . Z h a n g , E . G . C o l l i n s J r , D . S h i , " C e n t r a l i z e d a n d d i s t r i b u t e d t a s k allocation in multi-robot teams via a stochastic clustering auction." ACM Transactions on Autonomous and Adaptive Systems (TAAS) 7.2 (2012): 21

work page 2012
[30]

A modified greedy algorithm for the task assignment problem

A. M. Douglas, "A modified greedy algorithm for the task assignment problem." University of Louisville, (2007). Electronic Theses and Dissertations. Paper 369

work page 2007
[31]

A distributed algorithm for the assignment problem

D. P. Bertsekas, "A distributed algorithm for the assignment problem." Laboratory for Information and Decision Systems Working Paper, Massachusetts Institute of Technology, Cambridge, MA (1979)

work page 1979

[1] [1]

A survey of cognitive and agent architectures

Wray, Robert, et al. "A survey of cognitive and agent architectures." University of Michigan (1994)

work page 1994

[2] [2]

Integrated cognitive architectures: a survey

Chong, Hui-Qing, Ah-Hwee Tan, and Gee-Wah Ng. "Integrated cognitive architectures: a survey." Artificial Intelligence Review 28.2 (2007): 103- 130

work page 2007

[3] [3]

The Soar cognitive architecture

Laird, John E. The Soar cognitive architecture. MIT Press, 2012

work page 2012

[4] [4]

The Architecture of Cognition’, Harvard University Press, Cambridge, MA

Anderson, John R. "The Architecture of Cognition’, Harvard University Press, Cambridge, MA." (1983)

work page 1983

[5] [5]

Anderson Richard King

Mellon, John R. Anderson Richard King. How can the human mind occur in the physical universe?. Oxford University Press, USA, 2007

work page 2007

[6] [6]

An integrated theory of the mind

J. R. Anderson, Bothell, M.D. Byrne, S. Douglass, C. Lebiere, & Y. Qin, “An integrated theory of the mind”. Psychological Review 111, (4), 2004

work page 2004

[7] [7]

Hardware Accelerated Cognitively Enhanced Complex Event Processing

T. Atahary, T. Taha, S. Douglass, “Hardware Accelerated Cognitively Enhanced Complex Event Processing”, 14th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, July, SNPD 2013

work page 2013

[8] [8]

The power of events: An introduction to complex event processing in distributed enterprise systems

D. Luckham, “The power of events: An introduction to complex event processing in distributed enterprise systems”. Springer Berlin Heidelberg, 2008

work page 2008

[9] [9]

Concurrent knowledge activation calculation in large declarative memories

S. Douglass, C. Myers, “Concurrent knowledge activation calculation in large declarative memories”, Proceedings of the 10th International Conference on Cognitive Modeling, 55–60, 2010

work page 2010

[10] [10]

Esper available: http://esper.codehaus.org/

work page

[11] [11]

Knowledge mining for cognitive agents through path based forward checking,

T. Atahary, T. Taha, F. Webber, amd S. Douglass, “Knowledge mining for cognitive agents through path based forward checking,” 16th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), pp. 1-8, June, 2015

work page 2015

[12] [12]

Parallelizing knowledge mining in a cognitive agent for autonomous decision making,

T. Atahary, T. Taha and S. Douglass, "Parallelizing knowledge mining in a cognitive agent for autonomous decision making," 2017 Computing Conference, London, 2017, pp. 1058-1068

work page 2017

[13] [13]

Cognitive computing building block: A versatile and efficient digital neuron model for neurosynaptic cores,

A. S. Cassidy, P. Merolla, J. V. Arthur, S. K. Esser, B. Jackson, R. Alvarez-Icaza, P. Datta, J. Sawada, T. M. Wong, V. Feldman, A. Amir, D. B.-D. Rubin, F. Akopyan, E. McQuinn, W. P. Risk, and D. S. Modha “Cognitive computing building block: A versatile and efficient digital neuron model for neurosynaptic cores,” International Joint Conference on Neural ...

work page 2013

[14] [14]

Cognitive computing programming paradigm: A Corelet Language for composing networks of neurosynaptic cores,

A. Amir, P. Datta, W. P. Risk, A. S. Cassidy, J. A. Kusnitz, S. K. Esser, A. Andreopoulos, T. M. Wong, M. Flickner, R. Alvarez-Icaza, E. McQuinn, B. Shaw, N. Pass, and D. S. Modha, “Cognitive computing programming paradigm: A Corelet Language for composing networks of neurosynaptic cores,” pp. 1-10, Dallas, TX, August 2013

work page 2013

[15] [15]

Memristor Crossbar Based Multicore Neuromorphic Processors,

T. M. Taha, R. Hasan, and C. Yakopcic, “Memristor Crossbar Based Multicore Neuromorphic Processors,” IEEE International System-on- Chip Conference (SOCC), pp. 383-389, Las Vegas, NV, Sept. 2014

work page 2014

[16] [16]

Flexible Memristor Based Neuromorphic System for Implementing Multi-layer Neural Network Algorithms,

C. Yakopcic, R. Hasan, and T. M. Taha, "Flexible Memristor Based Neuromorphic System for Implementing Multi-layer Neural Network Algorithms," International Journal of Parallel, Emergent and Distributed Systems, vol. 33, no. 4, pp. 408-429, 2018

work page 2018

[17] [17]

Extremely Parallel Memristor Crossbar Architecture for Convolutional Neural Network Implementation,

C. Yakopcic, Z. Alom and T. Taha, “Extremely Parallel Memristor Crossbar Architecture for Convolutional Neural Network Implementation,” IEEE/INNS International Joint Conference on Neural Networks (IJCNN), pp. 1696-1703, Anchorage, AK, May 2017

work page 2017

[18] [18]

Method for ex-situ training in a memristor-based neuromorphic circuit using a robust weight programming method,

C. Yakopcic, T. M. Taha, M. R. McLean, “Method for ex-situ training in a memristor-based neuromorphic circuit using a robust weight programming method,” Electronics Letters, vol. 51, no. 12, pp. 899-900, 2015

work page 2015

[19] [19]

Memristor Crossbar Deep Network Implementation Based on a Convolutional Neural Network,

C. Yakopcic, M. Z. Alom, and T. M. Taha, “Memristor Crossbar Deep Network Implementation Based on a Convolutional Neural Network,” IEEE/INNS International Joint Conference on Neural Networks (IJCNN), pp. 963-970, Vancouver, BC, July 2016

work page 2016

[20] [20]

Cognitive Domain Ontologies in Lookup Tables Stored in a Memristor String Matching Architecture,

N . R a h m a n , C . Y a k o p c i c , T . A t a h a r y , R . H a s a n , T . M . T a h a , a n d S . Douglass, “Cognitive Domain Ontologies in Lookup Tables Stored in a Memristor String Matching Architecture,” 30th annual IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), pp. 1-4, Windsor, Ontario, April 2017

work page 2017

[21] [21]

Cognitive Domain Ontologies in a Memristor Crossbar Architecture,

C. Yakopcic, N. Rahman, T. Atahary, T. M. Taha, and S. Douglass, “Cognitive Domain Ontologies in a Memristor Crossbar Architecture,” IEEE National Aerospace and Electronics Conference (NAECON), pp. 76-83, Dayton, OH, June 2017

work page 2017

[22] [22]

Task Allocation Performance Comparison for Low Power Devices,

N. Rahman, T. Atahary, C. Yakopcic, T. M. Taha, Scott Douglass, “Task Allocation Performance Comparison for Low Power Devices,” IEEE National Aerospace and Electronics Conference (NAECON), pp. 247- 253, Dayton, OH, July, 2018

work page 2018

[23] [23]

High Speed Approximate Cognitive Domain Ontologies for Asset Allocation based on Isolated Spiking Neurons,

C. Yakopcic, T. Atahary, T. M. Taha, A. Beigh, and S. Douglass, “High Speed Approximate Cognitive Domain Ontologies for Asset Allocation based on Isolated Spiking Neurons,” IEEE National Aerospace and Electronics Conference (NAECON), pp. 241-246, Dayton, OH, July, 2018

work page 2018

[24] [24]

Loihi: A Neuromorphic Manycore Processor with On-Chip Learning,

M. Davies, N. Srinivasa, T.-H. Lin, G. Chinya, Y. Cao, S. H. Choday, G. Dimou, P. Joshi, N. Imam, S. Jain, Y. Liao, C.-K. Lin, A. Lines, R. Liu, D. Mathaikutty, S. McCoy, A. Paul, J. Tse, G. Venkataramanan, Y.-H. Weng, A. Wild, Y. Yang, H. Wang, “Loihi: A Neuromorphic Manycore Processor with On-Chip Learning,” IEEE Micro, vol. 38, no. 1, pp. 82- 99, 2018

work page 2018

[25] [25]

Programming Spiking Neural Networks on Intel’s Loihi,

C.-K. Lin, A. Wild, G. N. Chinya, Y. Cao, M. Davies, D. M. Lavery, H. Wang, “Programming Spiking Neural Networks on Intel’s Loihi,” Computer, vol. 51, no. 3, pp. 52-61, 2018

work page 2018

[26] [26]

Benchmarking Keyword Spotting Efficiency on Neuromorphic Hardware

P. Blouw, X. Choo, E. Hunsberger, C. Eliasmith, “Benchmarking Keyword Spotting Efficiency on Neuromorphic Hardware,” arXiv :1812.01739, submitted 4 Dec. 2018

work page internal anchor Pith review Pith/arXiv arXiv 2018

[27] [27]

Methods for task allocation via agent coalition formation

O. Shehory, S. Kraus, “Methods for task allocation via agent coalition formation.” Artificial intelligence 101.1-2 (1998): 165-200

work page 1998

[28] [28]

Multi-task allocation and path planning for cooperating UAVs

J. Bellingham, M. Tillerson, A. Richards, J. P. How, "Multi-task allocation and path planning for cooperating UAVs." Cooperative control: models, applications and algorithms. Springer, Boston, MA,

work page

[29] [29]

C e n t r a l i z e d a n d d i s t r i b u t e d t a s k allocation in multi-robot teams via a stochastic clustering auction

K . Z h a n g , E . G . C o l l i n s J r , D . S h i , " C e n t r a l i z e d a n d d i s t r i b u t e d t a s k allocation in multi-robot teams via a stochastic clustering auction." ACM Transactions on Autonomous and Adaptive Systems (TAAS) 7.2 (2012): 21

work page 2012

[30] [30]

A modified greedy algorithm for the task assignment problem

A. M. Douglas, "A modified greedy algorithm for the task assignment problem." University of Louisville, (2007). Electronic Theses and Dissertations. Paper 369

work page 2007

[31] [31]

A distributed algorithm for the assignment problem

D. P. Bertsekas, "A distributed algorithm for the assignment problem." Laboratory for Information and Decision Systems Working Paper, Massachusetts Institute of Technology, Cambridge, MA (1979)

work page 1979