scholarly journals Autonomous Evolution of Topographic Regularities in Artificial Neural Networks

2010 ◽  
Vol 22 (7) ◽  
pp. 1860-1898 ◽  
Author(s):  
Jason Gauci ◽  
Kenneth O. Stanley
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Evolutionary Algorithms ◽  
Neural Computation ◽  
Topographic Maps ◽  
The Novel ◽  
The Past ◽  
Connectivity Patterns ◽  
Artificial Neural ◽  
Autonomous Evolution

Looking to nature as inspiration, for at least the past 25 years, researchers in the field of neuroevolution (NE) have developed evolutionary algorithms designed specifically to evolve artificial neural networks (ANNs). Yet the ANNs evolved through NE algorithms lack the distinctive characteristics of biological brains, perhaps explaining why NE is not yet a mainstream subject of neural computation. Motivated by this gap, this letter shows that when geometry is introduced to evolved ANNs through the hypercube-based neuroevolution of augmenting topologies algorithm, they begin to acquire characteristics that indeed are reminiscent of biological brains. That is, if the neurons in evolved ANNs are situated at locations in space (i.e., if they are given coordinates), then, as experiments in evolving checkers-playing ANNs in this letter show, topographic maps with symmetries and regularities can evolve spontaneously. The ability to evolve such maps is shown in this letter to provide an important advantage in generalization. In fact, the evolved maps are sufficiently informative that their analysis yields the novel insight that the geometry of the connectivity patterns of more general players is significantly smoother and more contiguous than less general ones. Thus, the results reveal a correlation between generality and smoothness in connectivity patterns. They also hint at the intriguing possibility that as NE matures as a field, its algorithms can evolve ANNs of increasing relevance to those who study neural computation in general.

scholarly journals INDUSTRIAL APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS

2014 ◽  
pp. 8-20
Author(s):  
Kurosh Madani
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Real World ◽  
Industrial Applications ◽  
Large Field ◽  
Nonlinear Functions ◽  
The Past ◽  
Real World Applications ◽  
Ann Models ◽  
Artificial Neural

In a large number of real world dilemmas and related applications the modeling of complex behavior is the central point. Over the past decades, new approaches based on Artificial Neural Networks (ANN) have been proposed to solve problems related to optimization, modeling, decision making, classification, data mining or nonlinear functions (behavior) approximation. Inspired from biological nervous systems and brain structure, Artificial Neural Networks could be seen as information processing systems, which allow elaboration of many original techniques covering a large field of applications. Among their most appealing properties, one can quote their learning and generalization capabilities. The main goal of this paper is to present, through some of main ANN models and based techniques, their real application capability in real world industrial dilemmas. Several examples through industrial and real world applications have been presented and discussed.

Neural computation, architecture, and evolution

1997 ◽  
Vol 20 (1) ◽  
pp. 80-80
Author(s):  
Paul Skokowski
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Neural Computation ◽  
Artificial Neural ◽  
The Brain

Biological neural computation relies a great deal on architecture, which constrains the types of content that can be processed by distinct modules in the brain. Though artificial neural networks are useful tools and give insight, they cannot be relied upon yet to give definitive answers to problems in cognition. Knowledge re-use may be driven more by architectural inheritance than by epistemological drives.

Evolutionary Approaches for ANNs Design

2011 ◽  
pp. 575-580
Author(s):  
Antonia Azzini ◽  
Andrea G.B. Tettamanzi
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Evolutionary Algorithms ◽  
Computational Models ◽  
Artificial Neurons ◽  
Important Research Topic ◽  
Recent Developments ◽  
Evolving System ◽  
Artificial Neural ◽  
Ann Application

Artificial neural networks (ANNs) are computational models, loosely inspired by biological neural networks, consisting of interconnected groups of artificial neurons which process information using a connectionist approach. ANNs are widely applied to problems like pattern recognition, classification, and time series analysis. The success of an ANN application usually requires a high number of experiments. Moreover, several parameters of an ANN can affect the accuracy of solutions. A particular type of evolving system, namely neuro-genetic systems, have become a very important research topic in ANN design. They make up the so-called Evolutionary Artificial Neural Networks (EANNs), i.e., biologicallyinspired computational models that use evolutionary algorithms (EAs) in conjunction with ANNs. Evolutionary algorithms and state-of-the-art design of EANN were introduced first in the milestone survey by Xin Yao (1999), and, more recently, by Abraham (2004), by Cantu-Paz and Kamath (2005), and then by Castellani (2006). The aim of this article is to present the main evolutionary techniques used to optimize the ANN design, providing a description of the topics related to neural network design and corresponding issues, and then, some of the most recent developments of EANNs found in the literature. Finally a brief summary is given, with a few concluding remarks.

scholarly journals In search of a warning strategy against exchange-rate attacks: Forecasting tactics using artificial neural networks

2000 ◽  
Vol 5 (2) ◽  
pp. 121-137
Author(s):  
A. S. Andreou ◽  
G. A. Zombanakis ◽  
E. F. Georgopoulos ◽  
S. D. Likothanassis
Keyword(s):  
Neural Networks ◽  
Genetic Algorithms ◽  
Artificial Neural Networks ◽  
Discrete Dynamics ◽  
Domestic Currency ◽  
Heart Attacks ◽  
The Past ◽  
Forecasting Performance ◽  
Successful Prediction ◽  
Artificial Neural

“Heart attacks and devaluations are not predictable and, certainly, are never preannounced”. (The usual remark made by government spokesmen shortly after a domestic currency devaluation has taken place.)The contribution that this paper aspires to make is the prediction of an oncoming attack against the domestic currency, something that is expected to increase the possibilities of successful hedging by the authorities. The analysis has focused on the Greek Drachma, which has suffered a series of attacks during the past few years, thus offering a variety of such “shock” incidents accompanied by frequent interventions by the authorities. The prediction exercised here is performed in a discrete dynamics environment, based on the daily fluctuations of the interbank overnight interest rate, using artificial neural networks enhanced by genetic algorithms. The results obtained on the basis of the forecasting performance have been considered most encouraging, in providing a successful prediction of an oncoming attack against the domestic currency.

scholarly journals High-Performance Tracking for Piezoelectric Actuators Using Super-Twisting Algorithm Based on Artificial Neural Networks

Mathematics ◽  
2021 ◽  
Vol 9 (3) ◽  
pp. 244
Author(s):  
Cristian Napole ◽  
Oscar Barambones ◽  
Mohamed Derbeli ◽  
Isidro Calvo ◽  
Mohammed Yousri Silaa ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
High Performance ◽  
Piezoelectric Actuators ◽  
The Novel ◽  
Tracking Accuracy ◽  
Novel Structure ◽  
Novel Approach ◽  
Artificial Neural ◽  
Twisting Algorithm

Piezoelectric actuators (PEA) are frequently employed in applications where nano-Micr-odisplacement is required because of their high-precision performance. However, the positioning is affected substantially by the hysteresis which resembles in an nonlinear effect. In addition, hysteresis mathematical models own deficiencies that can influence on the reference following performance. The objective of this study was to enhance the tracking accuracy of a commercial PEA stack actuator with the implementation of a novel approach which consists in the use of a Super-Twisting Algorithm (STA) combined with artificial neural networks (ANN). A Lyapunov stability proof is bestowed to explain the theoretical solution. Experimental results of the proposed method were compared with a proportional-integral-derivative (PID) controller. The outcomes in a real PEA reported that the novel structure is stable as it was proved theoretically, and the experiments provided a significant error reduction in contrast with the PID.

scholarly journals Augmented reality using artificial neural networks –a review

2019 ◽  
Vol 8 (4) ◽  
pp. 603
Author(s):  
Sreekumar Narayanan ◽  
Srinath Doss
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Augmented Reality ◽  
Effective Utilization ◽  
The Past ◽  
Diverse Application ◽  
The Common ◽  
Artificial Neural ◽  
The Military ◽  
The Way

The present paper reviews the areas where Augmented Reality (AR) has been used in Artificial Neural Networks (ANN) (Artificial Neural Networks). The focus on systems based on AR is largely on enhancing technologies in diverse application areas such as; defense, robotics, medical, manufacturing, education, entertainment, assisted driving, maintenance and mobile assistance. However, AR is now finding much usage in ANN. The research considered a review based methodology wherein most studies conducted in the past on AR and ANN were reviewed. AR with ANN has profound applications in various sectors and has been developed in an extended way but still has some distance to go afore industries, the military and the common public will receive it as a accustomed user interface. AR would modernize the way people animate and the way industries endeavor by effective utilization. There is an incredible potential in fields such as construction, art, architecture, repair and manufacturing with mediated reality and well-organized visualization through AR.  

Sign in / Sign up

Export Citation Format

Share Document