About: Towards Dendrite Spherical Neurons for Pattern Classification

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Towards Dendrite Spherical Neurons for Pattern Classification Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : covidontheweb.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Towards Dendrite Spherical Neurons for Pattern Classification
Creator	Gómez-Flores, Wilfrido Sossa-Azuela, Juan
Source	PMC
abstract	This paper introduces the Dendrite Spherical Neuron (DSN) as an alternative to the Dendrite Ellipsoidal Neuron (DEN), in which hyperspheres group the patterns from different classes instead of hyperellipses. The reasoning behind DSN is simplifying the computation of DEN architecture, where a centroid and covariance matrix are two dendritic parameters, whereas, in DSN, the covariance matrix is replaced by a radius. This modification is useful to avoid singular covariance matrices since DEN requires measuring the Mahalanobis distance to classify patterns. The DSN training consists of determining the centroids of dendrites with the k-means algorithm, followed by calculating the radius of dendrites as the mean distance to the two nearest centroids, and finally determining the weights of a softmax function, with Stochastic Gradient Descent, at the output of the neuron. Besides, the Simulated Annealing automatically determines the number of dendrites that maximizes the classification accuracy. The DSN is applied to synthetic and real-world datasets. The experimental results reveal that DSN is competitive with Multilayer Perceptron (MLP) networks, with less complex architectures. Also, DSN tends to outperform the Dendrite Morphological Neuron (DMN), which uses hyperboxes. These findings suggest that the DSN is a potential alternative to MLP and DMN for pattern classification tasks.
has issue date	2020-04-29(xsd:dateTime)
bibo:doi	10.1007/978-3-030-49076-8_2
has license	no-cc
sha1sum (hex)	275933f9d7db97d865ea03df4a810f3b3f91202f
schema:url	https://doi.org/10.1007/978-3-030-49076-8_2
resource representing a document's title	Towards Dendrite Spherical Neurons for Pattern Classification
has PubMed Central identifier	PMC7297592
schema:publication	Pattern Recognition
resource representing a document's body	covid:275933f9d7db97d865ea03df4a810f3b3f91202f#body_text
is schema:about of	named entity 'Spherical' named entity 'Neuron' named entity 'dendrites' named entity 'introduces' named entity 'neuron' named entity 'training' named entity 'automatically' named entity 'The' named entity 'The' named entity 'covariance' named entity 'Dendrite' named entity 'softmax function' named entity 'alternative' named entity 'calculating' named entity 'DSN' named entity 'covariance matrix' named entity 'Neuron' named entity 'Neuron' named entity 'covariance matrix' named entity 'MLP' named entity 'centroids' named entity 'Stochastic Gradient Descent' named entity 'k-means algorithm' named entity 'MLP' named entity 'Pattern Classification' named entity 'dendrite' named entity 'MLP' named entity 'evolutionary computation' named entity 'heuristic methods' named entity 'Neurons' named entity 'pseudocode' named entity 'neuronal models' named entity 'k-means algorithm' named entity 'Multilayer Perceptron' named entity 'Ellipsoidal' named entity 'dendrite' named entity 'MLP' named entity 'Dendrite' named entity 'neurons' named entity 'covariance matrix' named entity 'dendrites' named entity 'Neurons' named entity 'dendrites' named entity 'neural models' named entity 'DNS' named entity 'pattern classification' named entity 'dendrites' named entity 'dendrite' named entity 'tuple' named entity 'grid search' named entity 'Algorithm' named entity 'hypersphere' named entity 'statistically significant' named entity 'dendrites' named entity 'dendrites' named entity 'Dendrite' named entity 'nonlinear' named entity 'cross-entropy' named entity 'dendrite' named entity 'dendrite' named entity 'dendrites' named entity 'MLP' named entity 'Dendrite' named entity 'Kruskal-Wallis' named entity 'linear combination' named entity 'neighborhood structure' named entity 'neuron' named entity 'dendrite' named entity 'biological neurons' named entity 'centroid' named entity 'dendrite' named entity 'dendrite' named entity 'dendrites' named entity 'variance' named entity 'Bonferroni method' named entity 'subset' named entity 'DNS' named entity 'neurons' named entity 'activation function' named entity 'neurons' named entity 'dendrites' named entity 'ANN'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software