Name: Investigation of Latent Space Representation Techniques for Networks (en Inglés)
SKU: 57219395
Price: 110190.00 CLP
Availability: InStock
Author: Nerurkar, Pranav
ISBN: 9786138913139

portada Investigation of Latent Space Representation Techniques for Networks (en Inglés)

Investigation of Latent Space Representation Techniques for Networks (en Inglés)

Formato

Libro Físico

Autor

Pranav Nerurkar

Editorial

Scholars' Press

Idioma

Inglés

N° páginas

168

Encuadernación

Tapa Blanda

Dimensiones

22.9x15.2x1 cm

Peso

0.25 kg.

ISBN13

9786138913139

Categorías

Tecnología de la información: cuestiones generales

Investigation of Latent Space Representation Techniques for Networks (en Inglés)

Pranav Nerurkar (Autor) · Scholars' Press · Tapa Blanda

Libro Nuevo Importado

Envío: 21 a 25 días háb.

$ 183.650$ 110.190

-40%

Costos de importación incluídos en el precio ✅

Libro Nuevo

Quedan 10 unidades

$ 110.190

Llega entre el 20 Oct y el 26 Oct a Santiago, Región Metropolitana. Seleccionar ubicación

Agregar a lista de deseos

Reseña del libro "Investigation of Latent Space Representation Techniques for Networks (en Inglés)"

A multitude of critical real-world or synthetic systems possesses network structure: citation networks, internet, protein-protein interactions, brain connectors data and social networking websites. Extending analytical techniques to process such non-euclidean data is, therefore, an essential direction for research. The focus of this research is on Latent Space Representations (L.S.R.) of networks, i.e., learning low dimension vector representations of network data. L.S.R. techniques have a data driven mechanism for learning vector embedding of network data structures. Learning vector space embedding of graph-structured is similar to mapping complex data into low-dimensional geometries. The embedding process minimizes drawbacks associated with graph-structured data. The key contributions of this work are: surveying state of the art L.S.R. techniques, performing extensive experiments on network data-sets, demonstrating the use of network science in understanding the structure and behavior in systems and investigating techniques for enhancing the performance of existing architectures for network representation learning.