Monotonic multi-layer perceptron networks as universal approximators

Authors:
Bernhard Lang
Affiliations:
Siemens AG, Corporate Technology, Munich, Germany
Venue:
ICANN'05 Proceedings of the 15th international conference on Artificial neural networks: formal models and their applications - Volume Part II
Year:
2005

Citing 3
Cited 4

Multilayer feedforward networks are universal approximators

Neural Networks
Hints

Neural Computation
Monotonic networks

NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems 10

Comparison of Neural Networks Incorporating Partial Monotonicity by Structure

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
How to select an optimal neural model of chemical reactivity?

Neurocomputing
2010 Special Issue: Comparison of universal approximators incorporating partial monotonicity by structure

Neural Networks
Calibrating artificial neural networks by global optimization

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

Multi-layer perceptron networks as universal approximators are well-known methods for system identification. For many applications a multi-dimensional mathematical model has to guarantee the monotonicity with respect to one or more inputs. We introduce the MONMLP which fulfils the requirements of monotonicity regarding one or more inputs by constraints in the signs of the weights of the multi-layer perceptron network. The monotonicity of the MONMLP does not depend on the quality of the training because it is guaranteed by its structure. Moreover, it is shown that in spite of its constraints in signs the MONMLP is a universal approximator. As an example for model predictive control we present an application in the steel industry.