Genetic Network Architecture Search
This work addresses architecture search for computer vision tasks, but it is incremental as it builds on existing genetic algorithm and SGD methods.
The paper tackles the problem of neural network architecture design by proposing a genetic algorithm integrated with SGD to search for optimal convolutional cell structures, achieving 96% accuracy on CIFAR10 and 80.1% on CIFAR100.
We propose a method for learning the neural network architecture that based on Genetic Algorithm (GA). Our approach uses a genetic algorithm integrated with standard Stochastic Gradient Descent(SGD) which allows the sharing of weights across all architecture solutions. The method uses GA to design a sub-graph of Convolution cell which maximizes the accuracy on the validation-set. Through experiments, we demonstrate this methods performance on both CIFAR10 and CIFAR100 dataset with an accuracy of 96% and 80.1%. The code and result of this work available in GitHub:https://github.com/haihabi/GeneticNAS.