Differential Evolution Training Algorithm for Feed-Forward Neural Networks

By Jarmo Ilonen, Joni-Kristian Kamarainen, Jouni Lampinen. Neural Processing Letters, 2003

638 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/c59d35d4ff8726becf83ed5b0665f1c438baa3df

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Differential Evolution Algorithm With Strategy Adaptation for Global Numerical Optimization (2009, background): “DE has been successfully applied in diverse fields such as mechanical engineering [13], [14], communication [11], and pattern recognition [10].”
Optimizing connection weights in neural networks using the whale optimization algorithm (2016, methodology): “DE and ES were applied in training MLP networks and compared to other techniques in different studies (Wdaa 2008; Ilonen et al. 2003; Slowik and Bialko 2008; Wienholt 1993).”
Chaotic grasshopper optimization algorithm for global optimization (2019, methodology): “These efficient and robust algorithms are utilized to tackle various problems such as economic dispatch optimization [8], design of an IIR filter [9], node localization in wireless sensor networks [10], feature selection [11] and neural networks [12].”
Artificial Bee Colony (ABC) Optimization Algorithm for Training Feed-Forward Neural Networks (2007, methodology): “... of network paralysis . This saturation may occur for a number of reasons, most of which are easily avoided [3].In order to overcome the disadvantages of gradient based algorithms, many global optimization methods have been proposed for training feed-forward neural networks such as Genetic Algori”
A soft computing-based approach for integrated training and rule extraction from artificial neural networks: DIFACONN-miner (2010, background): “As such, it can be applied to global searches within the weight space of a typical feed forward ANN [17].”
A naive Bayes probability estimation model based on self-adaptive differential evolution (2014, background): “Each individual vector < m∗, p∗ > in initial population will experience the mutation process, in which specific mutation function will be designed.”
Classification of COVID-19 patients from chest CT images using multi-objective differential evolution–based convolutional neural networks (2020, background): “This evolution from one generation to another ensures that the individual has better qualities remains part of the population and weak individuals are removed with each iteration [43] .”
Self-adaptive differential evolution algorithm for numerical optimization (2005, background): “Its effectiveness and efficiency has been successfully demonstrated in many application fields such as pattern recognition [1], communication [2] and mechanical engineering [3].”