On the relationship between neural networks, pattern recognition and intelligence

Bezdek, James C.

doi:10.1016/0888-613x(92)90013-p

Cited by 108 publications

(31 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…CI, such as ANN, was first proposed by Bezdek [37] and it has gained much attention. CI is a set of "nature-inspired" computational algorithms and paradigms to model complex real-world problems for which conventional mathematical modeling can be useless.…”

Section: Group Methods Data Handling (Gmdh)mentioning

confidence: 99%

Empirical Equation Using GMDH Methodology for the Charged Particles Multiplicity Distribution in Hadronic Positron-Electron Annihilation

El‐Dahshan

El-Bakry

2017

EEJP

View full text Add to dashboard Cite

Multiplicity distributions are the most general characteristics of hadronic multiparticle production processes. The multiplicity distribution of hadronic positron-electron annihilation is investigated using group method data handling (GMDH) technique up to the highest available center of mass energy ( s ) (from 14 GeV to 206 GeV). We have obtained an empirical physical equation for the multiplicity distribution as a function of s and the charged multiplicity (n ch ) i. e.

show abstract

Section: Group Methods Data Handling (Gmdh)mentioning

confidence: 99%

Empirical Equation Using GMDH Methodology for the Charged Particles Multiplicity Distribution in Hadronic Positron-Electron Annihilation

El‐Dahshan

El-Bakry

2017

EEJP

View full text Add to dashboard Cite

show abstract

“…Despite its popularity nowadays, the term CI has had different definitions through the years in the scientific community and typically is seen as a separate area of artificial intelligence (AI) very related with soft computing or natural computation. For instance, the first CI definition is typically attributed to J.C. Bezdek who defined CI in 1992 as "Computational systems that depend on numerical data supplied by manufactured sensors and do not rely upon knowledge" [63]. Later, in 2002, Engelbrecht defined CI as "the study of adaptive mechanisms which enable or facilitate intelligent behavior in complex and changing environments" [64].…”

Section: Computational Intelligence For Complex Optimization Problem mentioning

confidence: 99%

Survey on Complex Optimization and Simulation for the New Power Systems Paradigm

et al. 2018

View full text Add to dashboard Cite

This survey provides a comprehensive analysis on recent research related to optimization and simulation in the new paradigm of power systems, which embraces the so-called smart grid. We start by providing an overview of the recent research related to smart grid optimization. From the variety of challenges that arise in a smart grid context, we analyze with a significance importance the energy resource management problem since it is seen as one of the most complex and challenging in recent research. The survey also provides a discussion on the application of computational intelligence, with a strong emphasis on evolutionary computation techniques, to solve complex problems where traditional approaches usually fail. The last part of this survey is devoted to research on large-scale simulation towards applications in electricity markets and smart grids. The survey concludes that the study of the integration of distributed renewable generation, demand response, electric vehicles, or even aggregators in the electricity market is still very poor. Besides, adequate models and tools to address uncertainty in energy scheduling solutions are crucial to deal with new resources such as electric vehicles or renewable generation. Computational intelligence can provide a significant advantage over traditional tools to address these complex problems. In addition, supercomputers or parallelism opens a window to refine the application of these new techniques. However, such technologies and approaches still need to mature to be the preferred choice in the power systems field. In summary, this survey provides a full perspective on the evolution and complexity of power systems as well as advanced computational tools, such as computational intelligence and simulation, while motivating new research avenues to cover gaps that need to be addressed in the coming years.

show abstract

“…Readers interested in the origins of the CI concept should consult references. [3][4][5] Rather than trying to differentiate between the two terms, we will follow the evolution of Soft Computing and trace this evolution within the context of creating SC based decision-making models.…”

Section: The Originsmentioning

confidence: 99%

Soft Computing: A Continuously Evolving Concept

Bonissone¹

2010

IJCIS

View full text Add to dashboard Cite

Abstract. Soft Computing (SC) is a concept with constantly evolving semantics, as researchers have adopted its main philosophy while adding various interpretations and facets to this concept. Originally defined as a loose association or partnership of components, SC has gone through several transformational phases. This paper will trace some of the phases experienced by the author as part of his understanding of the evolution of SC and its role in constructing decision-making models. The first phase is the hybridization phase, driven by the inherit ease of integration of SC components. The second phase is a two-level model characterization, based on the split between object-level and meta-level reasoning. This phase, inspired by traditional AI problem formulation, led to a third phase, in which we addressed the knowledge and meta-knowledge representation required by each of these reasoning levels using a linguistics analogy. The fourth phase is the extension of the heuristics used at the metalevel, e.g. Metaheuristics (MH's) from evolutionary algorithms to other search methods. The fifth and last phase, further described in this paper, is the proposal for a strong separation between offline MH's (used for design and tuning) and online MH's (used for models selection or aggregation.) This last view suggests a broader use of SC components, since it enables us to use hybrid SC techniques at each of the MH's levels as well as at the object level. Furthermore, this separation facilitates the model lifecycle management, which is required to maintain the models vitality and prevent their obsolescence over time.

show abstract

On the relationship between neural networks, pattern recognition and intelligence

Cited by 108 publications

References 8 publications

Empirical Equation Using GMDH Methodology for the Charged Particles Multiplicity Distribution in Hadronic Positron-Electron Annihilation

Empirical Equation Using GMDH Methodology for the Charged Particles Multiplicity Distribution in Hadronic Positron-Electron Annihilation

Survey on Complex Optimization and Simulation for the New Power Systems Paradigm

Soft Computing: A Continuously Evolving Concept

Contact Info

Product

Resources

About