A0229
Title: Optimal classification for functional data using deep neural network
Authors: Guanqun Cao - Auburn University (United States) [presenting]
Abstract: The optimal functional data classification problem is exploited via deep neural networks. A sharp non-asymptotic estimation error bound on the excess misclassification risk is established which achieves the minimax rates of convergence. In contrast to existing literature, the proposed deep neural network classifier is proven to achieve optimality without the knowledge of likelihood functions. This framework is further extended to accommodate general multi-dimensional functional data classification problems. We demonstrate the favourable finite sample performance of the proposed classifiers in various simulations and two real data applications, including the speech recognition data and the brain imaging data.
