Monotonic multi-layer perceptron networks as universal approximators

被引：0
|
作者：
Lang, B [1 ]
机构：
[1] Siemens AG, Corp Technol, D-81730 Munich, Germany
来源：
ARTIFICIAL NEURAL NETWORKS: FORMAL MODELS AND THEIR APPLICATIONS - ICANN 2005, PT 2, PROCEEDINGS | 2005年 / 3697卷
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
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.
引用
收藏
页码：31 / 37
页数：7
相关论文
共 50 条
  • [21] Multi-layer perceptron mapping on a SIMD architecture
    Vitabile, S
    Gentile, A
    Dammone, GB
    Sorbello, F
    [J]. NEURAL NETWORKS FOR SIGNAL PROCESSING XII, PROCEEDINGS, 2002, : 667 - 675
  • [22] Multi-Layer Perceptron for Sleep Stage Classification
    Yulita, Intan Nurma
    Rosadi, Rudi
    Purwani, Sri
    Suryani, Mira
    [J]. 2ND INTERNATIONAL CONFERENCE ON STATISTICS, MATHEMATICS, TEACHING, AND RESEARCH 2017, 2018, 1028
  • [23] Results of Bias-variance Tests on Multi-layer Perceptron Neural Networks
    Nortje, Wimpie D.
    Holm, Johann E.W.
    Hancke, Gerhard P.
    Rudas, Imre. J.
    Horvath, Laszlo
    [J]. Journal of Advanced Computational Intelligence and Intelligent Informatics, 2001, 5 (05) : 300 - 305
  • [24] On the evaluation of relevance learning by a multi-layer perceptron
    Suzuki, K
    Hashimoto, S
    [J]. PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), VOLS 1-5, 2005, : 3204 - 3209
  • [25] Input Relevance in Multi-Layer Perceptron for Fundraising
    Barro, Diana
    Barzanti, Luca
    Corazza, Marco
    Nardon, Martina
    [J]. MATHEMATICAL AND STATISTICAL METHODS FOR ACTUARIAL SCIENCES AND FINANCE, MAF2024, 2024, : 31 - 36
  • [26] An extension of multi-layer perceptron based on layer-topology
    Zuters, J
    [J]. ENFORMATIKA, VOL 7: IEC 2005 PROCEEDINGS, 2005, : 178 - 181
  • [27] An Extension of Multi-Layer Perceptron Based on Layer-Topology
    Zuters, Janis
    [J]. PROCEEDINGS OF WORLD ACADEMY OF SCIENCE, ENGINEERING AND TECHNOLOGY, VOL 7, 2005, 7 : 178 - 181
  • [28] Fetal ECG Extraction Using Multi-Layer Perceptron Neural Networks with Bayesian Approach
    Golzan, S. Mojtaba
    Hakimpour, Farzaneh
    Toolou, Alireza
    [J]. 4TH EUROPEAN CONFERENCE OF THE INTERNATIONAL FEDERATION FOR MEDICAL AND BIOLOGICAL ENGINEERING, 2009, 22 (1-3): : 311 - 317
  • [29] An immune and a gradient-based method to train multi-layer perceptron neural networks
    Pasti, Rodrigo
    de Castro, Leandro Nunes
    [J]. 2006 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORK PROCEEDINGS, VOLS 1-10, 2006, : 2075 - +
  • [30] Using Multi-Layer Perceptron and Complex Network Metrics to Estimate the Performance of Optical Networks
    de Araujo, Danilo R. B.
    Martins-Filho, Joaquim F.
    Bastos-Filho, Carmelo J. A.
    [J]. 2013 SBMO/IEEE MTT-S INTERNATIONAL MICROWAVE & OPTOELECTRONICS CONFERENCE (IMOC), 2013,
12345