User: Guest  Login
Document type:
Konferenzbeitrag 
Author(s):
Matthias Kissel, Klaus Diepold 
Title:
Sobolev Training with Approximated Derivatives for Black-Box Function Regression with Neural Networks 
Abstract:
With Sobolev Training, neural networks are trained to fit target output values as well as target derivatives with respect to the inputs. This leads to better generalization and fewer required training examples for certain problems. In this paper, we present a training pipeline that enables Sobolev Training for regression problems where target derivatives are not directly available. Thus, we propose to use a least-squares estimate of the target derivatives based on function values of neighboring...    »
 
Keywords:
Sobolev Training, Neural Networks, Machine Learning 
Book / Congress title:
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 
Year:
2019 
Quarter:
3. Quartal 
Year / month:
2019-09 
Month:
Sep 
Pages:
16 
Reviewed:
ja 
Language:
en 
TUM Institution:
Lehrstuhl für Datenverarbeitung