DeepAI AI Chat
Log In Sign Up

Deep Learning for Functional Data Analysis with Adaptive Basis Layers

by   Junwen Yao, et al.

Despite their widespread success, the application of deep neural networks to functional data remains scarce today. The infinite dimensionality of functional data means standard learning algorithms can be applied only after appropriate dimension reduction, typically achieved via basis expansions. Currently, these bases are chosen a priori without the information for the task at hand and thus may not be effective for the designated task. We instead propose to adaptively learn these bases in an end-to-end fashion. We introduce neural networks that employ a new Basis Layer whose hidden units are each basis functions themselves implemented as a micro neural network. Our architecture learns to apply parsimonious dimension reduction to functional inputs that focuses only on information relevant to the target rather than irrelevant variation in the input function. Across numerous classification/regression tasks with functional data, our method empirically outperforms other types of neural networks, and we prove that our approach is statistically consistent with low generalization error. Code is available at: <>.


page 1

page 2

page 3

page 4


A Functional approach for Two Way Dimension Reduction in Time Series

The rise in data has led to the need for dimension reduction techniques,...

Deep Dimension Reduction for Supervised Representation Learning

The success of deep supervised learning depends on its automatic data re...

Functional Inverse Regression in an Enlarged Dimension Reduction Space

We consider an enlarged dimension reduction space in functional inverse ...

Machine Learning Assisted Orthonormal Basis Selection for Functional Data Analysis

In implementations of the functional data methods, the effect of the ini...

Enhanced Change-Point Detection in Functional Means

A new dimension reduction methodology for change-point detection in func...

Equinox: neural networks in JAX via callable PyTrees and filtered transformations

JAX and PyTorch are two popular Python autodifferentiation frameworks. J...

On overcoming the Curse of Dimensionality in Neural Networks

Let H be a reproducing Kernel Hilbert space. For i=1,...,N, let x_i∈R^d ...

Code Repositories


This repository is for the paper "Deep Learning for Functional Data Analysis with Adaptive Basisi Layers", ICML 2021.

view repo