scholarly journals BIBLIOMETRIC MAPPING OF THE COMPUTATIONAL INTELLIGENCE FIELD

2007 ◽  
Vol 15 (05) ◽  
pp. 625-645 ◽  
Author(s):  
NEES JAN VAN ECK ◽  
LUDO WALTMAN
Keyword(s):  
Neural Networks ◽  
Evolutionary Computation ◽  
Computational Intelligence ◽  
Fuzzy Systems ◽  
Optimization Problems ◽  
Control Problems ◽  
Classification Problems ◽  
Current Structure ◽  
The Neural Networks ◽  
Regression Problems

In this paper, a bibliometric study of the computational intelligence field is presented. Bibliometric maps showing the associations between the main concepts in the field are provided for the periods 1996–2000 and 2001–2005. Both the current structure of the field and the evolution of the field over the last decade are analyzed. In addition, a number of emerging areas in the field are identified. It turns out that computational intelligence can best be seen as a field that is structured around four important types of problems, namely control problems, classification problems, regression problems, and optimization problems. Within the computational intelligence field, the neural networks and fuzzy systems subfields are fairly intertwined, whereas the evolutionary computation subfield has a relatively independent position.

A BIOLOGICALLY INSPIRED NEURAL NETWORK FOR DYNAMIC PROGRAMMING

2001 ◽  
Vol 11 (06) ◽  
pp. 561-572 ◽  
Author(s):  
ROSELI A. FRANCELIN ROMERO ◽  
JANUSZ KACPRYZK ◽  
FERNANDO GOMIDE
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Dynamic Programming ◽  
Optimization Problems ◽  
Direct Method ◽  
Fuzzy Decision Making ◽  
Fuzzy Decision ◽  
Biologically Inspired ◽  
The Neural Network ◽  
The Neural Networks

An artificial neural network with a two-layer feedback topology and generalized recurrent neurons, for solving nonlinear discrete dynamic optimization problems, is developed. A direct method to assign the weights of neural networks is presented. The method is based on Bellmann's Optimality Principle and on the interchange of information which occurs during the synaptic chemical processing among neurons. The neural network based algorithm is an advantageous approach for dynamic programming due to the inherent parallelism of the neural networks; further it reduces the severity of computational problems that can occur in methods like conventional methods. Some illustrative application examples are presented to show how this approach works out including the shortest path and fuzzy decision making problems.

A Comparative Analysis of a Novel Anomaly Detection Algorithm with Neural Networks

2020 ◽  
pp. 52-68
Author(s):  
Srijan Das ◽  
Arpita Dutta ◽  
Saurav Sharma ◽  
Sangharatna Godboley
Keyword(s):  
Neural Networks ◽  
Comparative Analysis ◽  
Anomaly Detection ◽  
Supervised Classification ◽  
Detection Algorithm ◽  
Classification Problems ◽  
Anomalous Data ◽  
Criterion Functions ◽  
The Neural Networks ◽  
Data Objects

Anomaly Detection is an important research domain of Pattern Recognition due to its effects of classification and clustering problems. In this paper, an anomaly detection algorithm is proposed using different primitive cost functions such as Normal Perceptron, Relaxation Criterion, Mean Square Error (MSE) and Ho-Kashyap. These criterion functions are minimized to locate the decision boundary in the data space so as to classify the normal data objects and the anomalous data objects. The authors proposed algorithm uses the concept of supervised classification, though it is very different from solving normal supervised classification problems. This proposed algorithm using different criterion functions has been compared with the accuracy of the Neural Networks (NN) in order to bring out a comparative analysis between them and discuss some advantages.

Deep support vector neural networks

2020 ◽  
Vol 27 (4) ◽  
pp. 389-402
Author(s):  
David Díaz-Vico ◽  
Jesús Prada ◽  
Adil Omari ◽  
José Dorronsoro
Keyword(s):  
Neural Networks ◽  
Sample Size ◽  
Deep Neural Networks ◽  
Support Vector ◽  
Classification Problems ◽  
Vector Machines ◽  
Training Cost ◽  
Regression Problems ◽  
Classification And Regression ◽  
Deep Support

Kernel based Support Vector Machines, SVM, one of the most popular machine learning models, usually achieve top performances in two-class classification and regression problems. However, their training cost is at least quadratic on sample size, making them thus unsuitable for large sample problems. However, Deep Neural Networks (DNNs), with a cost linear on sample size, are able to solve big data problems relatively easily. In this work we propose to combine the advanced representations that DNNs can achieve in their last hidden layers with the hinge and ϵ insensitive losses that are used in two-class SVM classification and regression. We can thus have much better scalability while achieving performances comparable to those of SVMs. Moreover, we will also show that the resulting Deep SVM models are competitive with standard DNNs in two-class classification problems but have an edge in regression ones.

scholarly journals Evolutionary Computation and Its Applications in Neural and Fuzzy Systems

2011 ◽  
Vol 2011 ◽  
pp. 1-20 ◽  
Author(s):  
Biaobiao Zhang ◽  
Yue Wu ◽  
Jiabin Lu ◽  
K.-L. Du
Keyword(s):  
Neural Networks ◽  
Evolutionary Algorithms ◽  
Structural Optimization ◽  
Evolutionary Computation ◽  
Fuzzy Systems ◽  
Parametric Optimization ◽  
Optimization Techniques ◽  
System Modelling ◽  
Discrete Optimization Problem ◽  
Conventional Optimization

Neural networks and fuzzy systems are two soft-computing paradigms for system modelling. Adapting a neural or fuzzy system requires to solve two optimization problems: structural optimization and parametric optimization. Structural optimization is a discrete optimization problem which is very hard to solve using conventional optimization techniques. Parametric optimization can be solved using conventional optimization techniques, but the solution may be easily trapped at a bad local optimum. Evolutionary computation is a general-purpose stochastic global optimization approach under the universally accepted neo-Darwinian paradigm, which is a combination of the classical Darwinian evolutionary theory, the selectionism of Weismann, and the genetics of Mendel. Evolutionary algorithms are a major approach to adaptation and optimization. In this paper, we first introduce evolutionary algorithms with emphasis on genetic algorithms and evolutionary strategies. Other evolutionary algorithms such as genetic programming, evolutionary programming, particle swarm optimization, immune algorithm, and ant colony optimization are also described. Some topics pertaining to evolutionary algorithms are also discussed, and a comparison between evolutionary algorithms and simulated annealing is made. Finally, the application of EAs to the learning of neural networks as well as to the structural and parametric adaptations of fuzzy systems is also detailed.

scholarly journals On the Application of Machine Learning Techniques to Regression Problems in Sea Level Studies

2019 ◽  
Vol 36 (9) ◽  
pp. 1889-1902
Author(s):  
Magnus Hieronymus ◽  
Jenny Hieronymus ◽  
Fredrik Hieronymus
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Sea Level ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Coastal Protection ◽  
High Temporal Resolution ◽  
Learning Techniques ◽  
The Neural Networks ◽  
Regression Problems

Long sea level records with high temporal resolution are of paramount importance for future coastal protection and adaptation plans. Here we discuss the application of machine learning techniques to some regression problems commonly encountered when analyzing such time series. The performance of artificial neural networks is compared with that of multiple linear regression models on sea level data from the Swedish coast. The neural networks are found to be superior when local sea level forcing is used together with remote sea level forcing and meteorological forcing, whereas the linear models and the neural networks show similar performance when local sea level forcing is excluded. The overall performance of the machine learning algorithms is good, often surpassing that of the much more computationally costly numerical ocean models used at our institute.

Computational Intelligence

2010 ◽  
pp. 111-136 ◽  
Author(s):  
Zude Zhou ◽  
Huaiqing Wang ◽  
Ping Lou
Keyword(s):  
Neural Networks ◽  
Genetic Algorithms ◽  
Computational Intelligence ◽  
Analytical Methods ◽  
Fuzzy Systems ◽  
Academic Community ◽  
Neural Computing ◽  
New Paradigm ◽  
Combined System ◽  
Robust System

In the 1990s, a new paradigm of science characterized by uncertainty, nonlinearity, and irreversibility and tackling complex problems was generally recognized by the academic community. In this new paradigm, traditional analytical methods are ineffectual, and there is recognition of the need to explore new methods to solve the more flexible, more robust system problems. In 1994 the first Computational Intelligence Conference in Orlando, Florida, US, first combined three different areas, smart neural networks, fuzzy systems and genetic algorithms, not only because the three have many similarities, but also because a properly combined system of the three is more effective than a system generated by one single technical field. Various theories and approaches of computational intelligence including neural computing, fuzzy computing and evolutional computing are comprehensively introduced in this chapter.

Sign in / Sign up

Export Citation Format

Share Document