Non-linear Functional Modeling using Neural Networks
Authors:
- Aniruddha Rajendra RaoARAniruddha Rajendra Rao
- Matthew ReimherrMRMatthew Reimherr
Preprint
Abstract
We introduce a new class of non-linear models for functional data based on neural networks. Deep learning has been very successful in non-linear 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 utilizes 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. The effectiveness of the proposed methods in handling complex functional models is demonstrated by comprehensive simulation studies and real data examples.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Parsimonious memory unit for recurrent neural networks with application to natural language processingNeurocomputing, 2018
- Satellite image classification using Genetic Algorithm trained radial basis function neural network, application to the detection of flooded areasJournal of Visual Communication and Image Representation, 2017
- Continuously dynamic additive models for functional dataJournal of Multivariate Analysis, 2016
- Multi-objective optimization for building retrofit: A model using genetic algorithm and artificial neural network and an applicationEnergy and Buildings, 2014
- Eigenvalue decay: A new method for neural network regularizationNeurocomputing, 2014
- Functional projection pursuit regressionTEST, 2012
- An artificial neural network (p,d,q) model for timeseries forecastingExpert Systems with Applications, 2010
- Multivariate calibration with single-index signal regressionChemometrics and Intelligent Laboratory Systems, 2009
- Theoretical Properties of Projection Based Multilayer Perceptrons with Functional InputsNeural Processing Letters, 2006
- Neural network approximation of continuous functionals and continuous functions on compactificationsNeural Networks, 1999