Tuning of the structure and parameters of neural network using an improved genetic algorithm
By F. Leung, Hak-Keung Lam, S. Ling, Peter Kwong-Shun Tam. 2001
856 citations recorded by the source corpus.
Subfields: Artificial Intelligence
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
- Corinna Cortes
- Seyedali Mirjalili
- Mehryar Mohri
- Vitaly Kuznetsov
- Andrew Lewis
- Ricardo de A. Araújo
- Silvio Romero Lemos de Meira
- Scott Yang
Citations in the corpus
- AdaNet: Adaptive Structural Learning of Artificial Neural Networks (2016, background): “L G ] 5 J u l 2016 3. adapts the structure and complexity of the network to the difficulty of the particular problem at hand, with no pre-defined architecture.”
- Evolutionary algorithms for hyperparameter tuning on neural networks models (2014, background): “In the case of ANN, the tuning of some hyperparameters such as layers, number of neurons, activation functions or recurrencies has been widely researched (Murata, Yoshizawa, and Amari 1994; Hagiwara, Toda, and Usui 1993; Panchal et al. 2010; Leung et al. 2003).”
- A hybrid model for high-frequency stock market forecasting (2015, methodology): “(2008) presented a procedure, called the phase adjustment procedure (PAP), for ANN models (multilayer perceptron like) built using a hybrid learning process composed by GA (Leung et al., 2003) and gradient-based techniques (Battiti, 1992; Hagan & Menhaj, 1994; Moller, 1993; Riedmiller & Braun, 1993)”
- A review on weight initialization strategies for neural networks (2021, methodology): “The proposed methodology was tested on five benchmark datasets and compared with the techniques proposed by Leung et al. (2003) and Cao et al. (2012) and Levenberg–Marquardt algorithm.”
- Personal recommendation using deep recurrent neural networks in NetEase (2016, methodology): “Previous work [12][25] adopted the genetic algorithm to tune the structure of the neural network.”
- Let a biogeography-based optimizer train your Multi-Layer Perceptron (2014, methodology): “Leung et al. used the last method to tune the parameters of an FNN utilizing EAs [30].”