Tuning the structure and parameters of a neural network by using hybrid Taguchi-genetic algorithm

By Jinn-Tsong Tsai, Jyh-Horng Chou, Tung-Kuan Liu. IEEE Transactions on Neural Networks, 2006

312 citations recorded by the source corpus.

How researchers see this paper

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

Artificial Bee Colony (ABC) Optimization Algorithm for Training Feed-Forward Neural Networks (2007, methodology): “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 Algorithms [4,5,6,7,8,9,10,11,12,13,14,15,16,17], The Particle Swarm Optimization algorithm [18, 19, 20, 22, 21, 23], Dif”
Hyperparameter Search in Machine Learning (2015, methodology): “A wide variety of optimization methods have been used for hyperparameter search, including particle swarm optimization [26, 27], genetic algorithms [32], coupled simulated annealing [33] and racing algorithms [6].”
Metaheuristic design of feedforward neural networks: A review of two decades of research (2017, methodology): “Similarly, in [210, 211], a hybrid Taguchi-genetic algorithm was proposed for optimizing the FNN architecture and weights, where authors used a genetic representation of the weights, but they select structure using constructive method (by adding hidden nodes one-by-one).”
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.”