Abstract
With the recent booming development of deep neural networks, the demand for automated design of efficient deep neural architectures has been increasing. This chapter introduces the basics of automated neural architecture search and discusses the current remaining challenges, focusing on scalability and flexibility of network architecture representation, effectiveness of search strategies and reduction of computational complexity in performance evaluations. Then, Bayesian optimization techniques used in neural architecture search are discussed. Finally, a random forest assisted neural architecture search algorithm is described and applied to convolutional neural network design, showing the effectiveness and efficiency of data-driven evolutionary optimization for deep neural architecture search.