Recurrent neural network as a KWTA selector: A synthesis procedure

Costea, Ruxandra L.; Marinov, Corneliu A.

doi:10.1109/iscas.2011.5937760

2011 IEEE International Symposium of Circuits and Systems (ISCAS) 2011

DOI: 10.1109/iscas.2011.5937760

|View full text |Cite

Recurrent neural network as a KWTA selector: A synthesis procedure

Ruxandra L. Costea

Corneliu A. Marinov

Abstract: A recurrent continuous time Hopfield network is rigorously designed to find the K largest elements in a list of currents. Simple formulae link the given parameters (as list separation and the processing time) with computed constants (as gain of amplifiers and interconnection conductance). The results unveil ways of improving circuit performances.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2019

Publication Types

Select...

Article1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

References 22 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

Design of a K-Winners-Take-All Model With a Binary Spike Train

Tymoshchuk

Wunsch

2019

IEEE Trans. Cybern.

View full text Add to dashboard Cite

A continuous-time K-winners-take-all (KWTA) neural model that can identify the largest K of N inputs, where command signal 1 łe K < N is described. The model is given by a differential equation where the spike train is a sum of delta functions. A functional block-diagram of the model includes N feed-forward hard-limiting neurons and one feedback neuron, used to handle input dynamics. The existence and uniqueness of the model steady states are analyzed, the convergence analysis of the state variable trajectories to the KWTA operation is proven, the convergence time and number of spikes required are derived, as well as the processing of time-varying inputs and perturbations of the model nonlinearities are analyzed. The main advantage of the model is that it is not subject to the intrinsic convergence of speed limitations of comparable designs. The model also has an arbitrary finite resolution determined by a given parameter, low complexity, and initial condition independence. Applications of the model for parallel sorting and parallel rank-order filtering are presented. Theoretical results are derived and illustrated with computer-simulated examples that demonstrate the model's performance.

show abstract

Design of a K-Winners-Take-All Model With a Binary Spike Train

Tymoshchuk

Wunsch

2019

IEEE Trans. Cybern.

View full text Add to dashboard Cite

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

hi@scite.ai

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Recurrent neural network as a KWTA selector: A synthesis procedure

Cited by 1 publication

References 22 publications

Design of a K-Winners-Take-All Model With a Binary Spike Train

Design of a K-Winners-Take-All Model With a Binary Spike Train

Contact Info

Product

Resources

About