Improved Cuckoo Search Algorithm for Feed forward Neural Network Training
International Journal of Artificial Intelligence & ApplicationsPublished 31 July 2011Open access
Ehsan Valian, Shahram Mohanna, Saeed Tavakoli
Citations273
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
An improved cuckoo search algorithm is proposed to enhance the accuracy and convergence rate of this algorithm, and is employed for training feedforward neural networks for two benchmark classification problems.
Abstract
The cuckoo search algorithm is a recently developed meta-heuristic optimization algorithm, which is suitable for solving optimization problems. To enhance the accuracy and convergence rate of this algorithm, an improved cuckoo search algorithm is proposed in this paper. Normally, the parameters of the cuckoo search are kept constant. This may lead to decreasing the efficiency of the algorithm. To cope with this issue, a proper strategy for tuning the cuckoo search parameters is presented. Then, it is employed for training feedforward neural networks for two benchmark classification problems. Finally, the performance of the proposed algorithm is compared with that of the standard cuckoo search. Simulation results demonstrate the effectiveness of the proposed algorithm.
Keywords
Computer ScienceEngineering
Choice Reviews OnlineGenetic algorithms in search, optimization, and machine learning
49,278 Citations1989
This book brings together the computer techniques, mathematical tools, and research results that will enable both students and practitioners to apply genetic algorithms to problems in many fields.
ScienceOptimization by Simulated Annealing
44,600 Citations1983Scott Kirkpatrick, C. D. Gelatt +1 more
A detailed analogy with annealing in solids provides a framework for optimization of the properties of very large and complex systems.
The MIT Press eBooksAdaptation in Natural and Artificial Systems
35,568 Citations1992John H. Holland
Initially applying his concepts to simply defined artificial systems with limited numbers of parameters, Holland goes on to explore their use in the study of a wide range of complex, naturally occuring processes, concentrating on systems having multiple factors that interact in nonlinear ways.
IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)Ant system: optimization by a colony of cooperating agents
11,908 Citations1996Marco Dorigo, Vittorio Maniezzo +1 more
Cuckoo Search via Lévy flights
6,089 Citations2009Xin‐She Yang, Suash Deb
A new meta-heuristic algorithm, called Cuckoo Search (CS), is formulated, based on the obligate brood parasitic behaviour of some cuckoo species in combination with the Lévy flight behaviour ofSome birds and fruit flies, for solving optimization problems.
CERN Document Server (European Organization for Nuclear Research)Fundamentals of neural networks: architectures, algorithms, and applications
3,046 Citations1994Laurene V. Fausett
Genetic programming: a paradigm for genetically breeding populations of computer programs to solve problems
602 Citations1990John R. Koza
In this new "genetic programming" paradigm, populations of computer programs are genetically bred using the Darwinian principle of survival of the fittest and using a genetic crossover (recombination) operator appropriate for genetically mating computer programs.
Decision SciencesNeural Networks: A New Tool for Predicting Thrift Failures*
534 Citations1992Linda Salchenberger, E. Mine Çinar +1 more
A neural network model that processes input data consisting of financial ratios is developed to predict the financial health of thrift institutions and its ability to discriminate between healthy and failed institutions is compared to a traditional statistical model.
Decision Support SystemsToward global optimization of neural networks: A comparison of the genetic algorithm and backpropagation
263 Citations1998Randall S. Sexton, Robert E. Dorsey +1 more
It is demonstrated that the genetic algorithm cannot only serve as a global search algorithm but by appropriately defining the objective function it can simultaneously achieve a parsimonious architecture.
Differential evolution design of an IIR-filter
260 Citations2002Rainer Storn
The task of designing an 18 parameter IIR-filter which has to meet tight specifications for both magnitude response and group delay is investigated and the usage of the general purpose minimization method Differential Evolution (DE) allows to perform the filter design with a minimum knowledge about digital filters.
OmegaComparing backpropagation with a genetic algorithm for neural network training
248 Citations1999Jatinder N.D. Gupta, Randall S. Sexton
It is shown that the use of a genetic algorithm can provide better results for training a feedforward neural network than the traditional techniques of backpropagation.
IEEE Transactions on Geoscience and Remote SensingDynamic differential evolution strategy and applications in electromagnetic inverse scattering problems
191 Citations2005Anyong Qing
It has been observed that the dynamic differential evolution strategy significantly outperforms the differential Evolution strategy in efficiency, robustness, and memory requirement.
arXiv (Cornell University)Engineering Optimisation by Cuckoo Search
137 Citations2010Xin‐She Yang, Suash Deb
Expert Systems with ApplicationsParticle swarm optimization for pap-smear diagnosis
82 Citations2007Yannis Marinakis, Magdalene Marinaki +1 more
A metaheuristic algorithm is proposed in order to classify the cells of pap-smear cells and shows that classification accuracy generally outperforms other previously applied intelligent approaches.
OmegaNeural networks: a need for caution
72 Citations1997Bruce Curry, Phillip L. Morgan
It is suggested that the now traditional method of backpropagation (BP) may not be the most appropriate basis for learning, based on the known deficiencies of gradient descent methods.
Information SciencesIntegrated multiobjective optimization and a priori preferences using genetic algorithms
66 Citations2007Javier Sanchis, M. Martínez +1 more
A new method to solve multiobjective optimization (MOO) problems is developed in which the user's information about his/her preferences is taken into account within the search process.
Harmony Search Based Supervised Training of Artificial Neural Networks
65 Citations2010Ali Mustafa, Rosni Abdullah +1 more
This paper proposes a training technique where two of HS probabilistic parameters are determined dynamically based on the best-to-worst harmony ratio in the current harmony memory instead of the improvisation count, more suitable for ANN training since parameters and termination would depend on the quality of the attained solution.
Mining Frequent Itemsets Using Genetic Algorithm
61 Citations2010Soumadip Ghosh, Sushanta Biswas +2 more
Differential Evolution and its Applications to Power Plant Control
49 Citations2007Joel H. Van Sickel, Kwang Y. Lee +1 more
A method of speeding up the convergence of differential evolution by combining it with aspects of standard evolutionary algorithms is included, and shows its uses in two applications.
A distributed discrete-time neural network architecture for pattern allocation and control
25 Citations2002Anthony T. Chronopoulos, J. Sarangapani
Genetic Algorithms for Optimal Design of Vehicle Suspensions
19 Citations2006Jingjun Zhang, Yanhong Zhang +1 more
The optimization results prove that the improved genetic algorithm is better than the numerical optimization method, the simple genetic algorithm and the niching genetic algorithm in the aspects of gaining global optimization solutions and accelerating convergence.