Issues in the Use of Neural Networks in Information Retrieval

verfasst von: Iuliana F. Iatan

Verlag: Springer International Publishing

Buchreihe : Studies in Computational Intelligence

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

This book highlights the ability of neural networks (NNs) to be excellent pattern matchers and their importance in information retrieval (IR), which is based on index term matching. The book defines a new NN-based method for learning image similarity and describes how to use fuzzy Gaussian neural networks to predict personality.It introduces the fuzzy Clifford Gaussian network, and two concurrent neural models: (1) concurrent fuzzy nonlinear perceptron modules, and (2) concurrent fuzzy Gaussian neural network modules.Furthermore, it explains the design of a new model of fuzzy nonlinear perceptron based on alpha level sets and describes a recurrent fuzzy neural network model with a learning algorithm based on the improved particle swarm optimization method.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Mathematical Aspects of Using Neural Approaches for Information Retrieval

Abstract

Scientists have shown considerable interest in the study of Artificial Neural Networks (NNs) during the last decade. Interest in Fuzzy Neural Network (FNN) applications was generated (Chen et al, IEEE Trans Syst Man Cybern 29(1):119–126, 1999, [1]) by two events.

Iuliana F. Iatan

Chapter 2. A Fuzzy Kwan–Cai Neural Network for Determining Image Similarity and for the Face Recognition

Abstract

Similarity is a crucial issue in Image Retrieval (Iatan and Worring, BioSystems (Under Review), 2016 [1]), (Nguyen and Worring, J Vis Lang Comput, 19:203–224, 2008 [2]), (Nguyen and Worring, ACM Trans Multimed Comput Commun Appl, 4(1):1–23, 2008, [3]), (Nguyen, Worring and Smeulders, Proceedings of the ACM SIGMM International Workshop on Multimedia Information Retrieval, pp. 107–116, 2006 [4]). It is relevant both for unsupervised clustering (Strong and Gong, Image Vis Comput, 29:774–786, 2011 [5]), (Chowhan, Int J Comput Electr Eng, 3(5):743–747, 2011 [6]) and for supervised classification (Hariri, Shokouhi and Mozayani, Iran J Electr Electron Eng, 4(3):79–93, 2008 [7]).

Iuliana F. Iatan

Chapter 3. Predicting Human Personality from Social Media Using a Fuzzy Neural Network

Abstract

Recently, ANNs methods have become useful for a wide variety of applications across a lot of disciplines and in particularly for prediction, where highly nonlinear approaches are required Bourdès et al., Adv Artif Neural Syst, pp 1–10, 2010, [1].

Iuliana F. Iatan

Chapter 4. Modern Neural Methods for Function Approximation

Abstract

Approximation or representation capabilities of NNs and fuzzy systems have attracted (Zeng, Keane, Goulermas and Liatsis, Approximation capabilities of hierarchical neural-fuzzy systems for function approximation on discrete spaces, 1:29–41, 2005, [1]) strong research in the past years. Application approaches with their solid results ilustrate that such approximations by the NNs have remarkable accuracy, especially by feedforward neural networks (FNNs) with one hidden layer.

Iuliana F. Iatan

Chapter 5. A Fuzzy Gaussian Clifford Neural Network

Abstract

A quick tour of relevant algebra is York and Yi, Clifford neural networks and chaotic time series. http://www.deepstem.com/Bio/SysSci-CNN-york.pdf, 2013, [1].

Iuliana F. Iatan

Chapter 6. Concurrent Fuzzy Neural Networks

Abstract

The aim of this chapter is to introduce two concurrent fuzzy neural network approaches for a: (1) Fuzzy Nonlinear Perceptron (FNP) and (2) Fuzzy Gaussian Neural Network (FGNN), each of them representing a winner-takes-all collection of fuzzy modules.

Iuliana F. Iatan

Chapter 7. A New Interval Arithmetic-Based Neural Network

Abstract

The aim of this chapter is to design a new model of fuzzy nonlinear perceptron, based on alpha level sets. The new model entitled Fuzzy Nonlinear Perceptron based on Alpha Level Sets (FNPALS) Iatan, Neuro-fuzzy system for pattern recognition (in Romanian), PhD thesis, 2003, [1], Iatan and de Rijke, A new interval arithmetic based neural network, 2014, [2] differs from the other fuzzy variants of the nonlinear perceptron, where the fuzzy numbers are represented by membership values. In the case of FNPALS, the fuzzy numbers are represented through the alpha level sets.

Iuliana F. Iatan

Chapter 8. A Recurrent Neural Fuzzy Network

Abstract

Besides the feedforward neural networks, there are the recurrent networks, where the impulses can be transmitted in both directions due to some reaction connections in these networks. Recurrent Neural Networks (RNNs) are linear or nonlinear dynamic systems. The dynamic behavior presented by the recurrent neural networks can be described both in continuous time, by differential equations and at discrete times by the recurrence relations (difference equations). The distinction between recurrent (or dynamic) neural networks and static neural networks is due to recurrent connections both between the layers of neurons of these networks and within the same layer, too. The aim of this chapter is to describe a Recurrent Fuzzy Neural Network (RFNN) model, whose learning algorithm is based on the Improved Particle Swarm Optimization (IPSO) method.

Iuliana F. Iatan

Titel: Issues in the Use of Neural Networks in Information Retrieval
verfasst von: Iuliana F. Iatan
Verlag: Springer International Publishing
Electronic ISBN: 978-3-319-43871-9
Print ISBN: 978-3-319-43870-2
DOI: https://doi.org/10.1007/978-3-319-43871-9