Description
Aniruddha Rajendra Rao, Ph.D.
Machine Learning Researcher
Hitachi America, Inc.
“Functional Neural Networks - Deep Learning for Functional Data”
We introduce a new class of nonlinear models for functional data based on neural networks. Deep learning has been very successful in nonlinear modeling, but there has been little work done in the functional data setting. We propose two variations of our framework: a functional neural network with continuous hidden layers, called the Functional Direct Neural Network (FDNN), and a second version that uses basis expansions and continuous hidden layers, called the Functional Basis Neural Network (FBNN). Both are designed explicitly to exploit the structure inherent in functional data. To fit these models, we derive a functional gradient-based optimization algorithm. We also propose a non-linear function-on-function approach, which consists of a functional encoder and a functional decoder, that gives a low-dimension latent representation of the time series data by reducing the number of functional features as well as the time points at which the functions are observed. The effectiveness of the proposed methods in handling complex functional models is demonstrated by comprehensive simulation studies and real data examples.
Biography
Dr. Rao is a Machine Learning Researcher at the Industrial AI Lab, Hitachi America, Ltd., R&D. His expertise includes Functional Data Analysis, Time Series, Machine Learning, and Deep Learning. He has published several papers on top-tier conferences/Journals and patents in this area. Rao has experience in domains like Supply Chain, Energy, Prognostics and Health Management and Automotive. He likes tackling open-ended problems and exploring new avenues to push research boundaries. He joined Hitachi America R&D in Oct 2021, before that, he got his Ph.D. in Statistics from Penn State University in the summer of 2021.
Functional Neural Networks - Deep Learning for Functional Data
Location
Online Meeting
Category:
Campus Events
