DNN- k WTA With Bounded Random Offset Voltage Drifts in Threshold Logic Units

The dual neural network-based [Formula Omitted]-winner-take-all (DNN-[Formula Omitted]WTA) is an analog neural model that is used to identify the [Formula Omitted] largest numbers from [Formula Omitted] inputs. Since threshold logic units (TLUs) are key elements in the model, offset voltage drifts i...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems 2022-07, Vol.33 (7), p.3184-3192
Main Authors: Lu, Wenhao, Leung, Chi-Sing, Sum, John, Xiao, Yi
Format: Article
Language:English
Subjects:
Convergence
Drift
Electric potential
Invariants
Neural networks
Take-all disease
Threshold logic
Voltage
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The dual neural network-based [Formula Omitted]-winner-take-all (DNN-[Formula Omitted]WTA) is an analog neural model that is used to identify the [Formula Omitted] largest numbers from [Formula Omitted] inputs. Since threshold logic units (TLUs) are key elements in the model, offset voltage drifts in TLUs may affect the operational correctness of a DNN-[Formula Omitted]WTA network. Previous studies assume that drifts in TLUs follow some particular distributions. This brief considers that only the drift range, given by [Formula Omitted], is available. We consider two drift cases: time-invariant and time-varying. For the time-invariant case, we show that the state of a DNN-[Formula Omitted]WTA network converges. The sufficient condition to make a network with the correct operation is given. Furthermore, for uniformly distributed inputs, we prove that the probability that a DNN-[Formula Omitted]WTA network operates properly is greater than [Formula Omitted]. The aforementioned results are generalized for the time-varying case. In addition, for the time-invariant case, we derive a method to compute the exact convergence time for a given data set. For uniformly distributed inputs, we further derive the mean and variance of the convergence time. The convergence time results give us an idea about the operational speed of the DNN-[Formula Omitted]WTA model. Finally, simulation experiments have been conducted to validate those theoretical results.
ISSN:2162-237X
2162-2388
DOI:10.1109/TNNLS.2021.3050493