Recombination of Artificial Neural Networks [article]

Aaron Vose, Jacob Balma, Alex Heye, Alessandro Rigazzi, Charles Siegel, Diana Moise, Benjamin Robbins, Rangan Sukumar
2019 arXiv   pre-print
We propose a genetic algorithm (GA) for hyperparameter optimization of artificial neural networks which includes chromosomal crossover as well as a decoupling of parameters (i.e., weights and biases) from hyperparameters (e.g., learning rate, weight decay, and dropout) during sexual reproduction. Children are produced from three parents; two contributing hyperparameters and one contributing the parameters. Our version of population-based training (PBT) combines traditional gradient-based
more » ... hes such as stochastic gradient descent (SGD) with our GA to optimize both parameters and hyperparameters across SGD epochs. Our improvements over traditional PBT provide an increased speed of adaptation and a greater ability to shed deleterious genes from the population. Our methods improve final accuracy as well as time to fixed accuracy on a wide range of deep neural network architectures including convolutional neural networks, recurrent neural networks, dense neural networks, and capsule networks.
arXiv:1901.03900v1 fatcat:kcxcxrd5lraafeyymfu3pnw5om