|
Activity Number:
|
487
- Neural Networks, Deep Learning, and RKHS
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 1, 2018 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistical Learning and Data Science
|
|
Abstract #329967
|
Presentation
|
|
Title:
|
Neural Network with Spline Smoothing and Its Applications to Genetics
|
|
Author(s):
|
Pei Geng* and Shan Zhang and Qing Lu
|
|
Companies:
|
Illinois State University and Michigan State University and Michigan State University
|
|
Keywords:
|
neural network;
spline smoothing;
back-propagation
|
|
Abstract:
|
In genetic association studies, the relationships between phenotypes and genotypes are often complicated and challenging to model. Hence we propose to adapt the spline smoothing in the neural network setup in hope to improve the performance of prediction and inference. Specifically, a cubic spline is fitted within each hidden layer and the fitted values on the grid points are used to generate the next hidden layer. Back-propagation is applied to implement the method. The performance of the proposed method and the traditional functional linear regression models are compared through simulation study.
|
Authors who are presenting talks have a * after their name.
