Dendrite Morphological Neural Networks trained by Differential Evolution

Arce, Fernando; Zamora, Erik; Sossa, Humberto; Barron, Randall F.

doi:10.1109/ssci.2016.7850259

Cited by 9 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A training and verification process was followed and produced an evolved material which was able to classify the two datasets without any metal-oxide-field-effect-transistors components. Results obtained were compared to different types of neural network solutions found in literature [1,8] as well as human diagnosis accuracy. In the case of the MMC dataset, the evolved carbon nanotube-based classifier produced average verification errors that were higher than both those obtained by human and neural networks.…”

Section: Discussionmentioning

confidence: 99%

“…For example, the difference between true and false positives, an important parameter in medical applications, was not used in our problem formulation. The above considerations will be addressed in further investigations, along with modifying the split of the MMC dataset to be the same as that used in [1].…”

Section: Discussionmentioning

confidence: 99%

“…The Fisher criterion over all attributes, as well as the measure of overlap defined in eqn. 2 are reported in Table I. A number of papers using the BPC dataset, such as [1,8], split it into K t = 276 and K v = 69, which are the values taken in our experiments. The MMC dataset on the other hand has been split arbitrarily into K t = 200 and K v = 630.…”

Section: Classification Problemsmentioning

confidence: 99%

“…They are compared with those achieved over a range of neural network (NN) implementations. Results for both BPC and MMC are reported in [1], where a dentrite morphological NN (DMNN) is trained using DE. Further BPC solutions obtained with five different types of NN are reported in Table II.…”

Section: A Medical Datasetsmentioning

confidence: 99%

See 3 more Smart Citations

Computing Based on Material Training: Application to Binary Classification Problems

Vissol-Gaudin¹,

Kotsialos²,

Groves³

et al. 2017

2017 IEEE International Conference on Rebooting Computing (ICRC)

View full text Add to dashboard Cite

any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Additional information:Use policyThe full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-prot purposes provided that:• a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in any format or medium without the formal permission of the copyright holders.Please consult the full DRO policy for further details. Abstract-Evolution-in-materio is a form of unconventional computing combining materials' training and evolutionary search algorithms. In previous work, a mixture of single-walled-carbonnanotubes (SWCNTs) dispersed in a liquid crystal (LC) was trained so that its morphology and electrical properties were gradually changed to perform a computational task. Materialbased computation is treated as an optimisation problem with a hybrid search space consisting of the voltages used for creating the electrical field and the material's infinitely possible SWCNT arrangements in LC. In this paper, we study solutions using synthetic data with a non-linear separating boundary. In addition, results for two real life datasets with partly merged classes are presented. The training process is based on a differential evolution (DE) algorithm, which subjects the SWCNT/LC material to repeated electrical charging, leading to progressive morphological and electric conductivity modifications. It is shown that the material configuration the DE algorithm converges to form a non-negligible part of the solution. Furthermore, the problem's complexity is relevant to the properties of the resulting physical solver. The material structures created when training for a problem allow the retraining for a less complex one. The result is a doubly-trained material that keeps the memory of the original more complex problem. This is not the case for doubly-trained materials where initial training is for the less complex problem. The optimal electric field found by the DE algorithm is also a necessary solution component for the material's output to be interpreted as a computation.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Classification Problemsmentioning

confidence: 99%

Section: A Medical Datasetsmentioning

confidence: 99%

See 2 more Smart Citations

Computing Based on Material Training: Application to Binary Classification Problems

Vissol-Gaudin¹,

Kotsialos²,

Groves³

et al. 2017

2017 IEEE International Conference on Rebooting Computing (ICRC)

View full text Add to dashboard Cite

show abstract

“…Interest in Morphological Neural Networks (MNNs) has increased in the last five years (Sossa, 2013), (Sossa, 2014), (Arce, 2016) and . This kind of ANNs make use of min and max operations to segment the input space into hyperboxes.…”

Section: Introductionmentioning

confidence: 99%

Efficient Lane Detection Based on Artificial Neural Networks

Arce

Zamora

Hernández

et al. 2017

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Lane detection is a problem that has attracted in the last years the attention of the computer vision community. Most of approaches used until now to face this problem combine conventional image processing, image analysis and pattern classification techniques. In this paper, we propose a methodology based on so-called Ellipsoidal Neural Networks with Dendritic Processing (ENNDPs) as a new approach to provide a solution to this important problem. The functioning and performance of the proposed methodology is validated with a real video taken by a camera mounted on a car circulating on urban highway of Mexico City.

show abstract