Control of Generalization with a Bi-Objective Sliding Mode Control Algorithm

Marcelo Azevdo Costa; Antônio Pádua Braga; Benjamin Rodrigues de Menezes; Gustavo Guimarães Parma; Roselito de Albuquerque Teixeria

doi:10.1109/SBRN.2002.1181432

Proceedings 7th Brazilian Symposium on Neurla Networks

Control of Generalization with a Bi-Objective Sliding Mode Control Algorithm

Year: 2002, Pages: 38

DOI Bookmark: 10.1109/SBRN.2002.1181432

Authors

Marcelo Azevdo Costa, Federal University of Minas Gerais
Antônio Pádua Braga, Federal University of Minas Gerais
Benjamin Rodrigues de Menezes, Federal University of Minas Gerais
Gustavo Guimarães Parma, Federal University of Minas Gerais
Roselito de Albuquerque Teixeria, Federal University of Minas Gerais

Abstract

This paper presents a new sliding mode control algorithm that is able to guide the trajectory of a Multi-Layer Perceptron (MLP) within the plane formed by the two objectives: training set error and norm of the weight vectors. The results show that the neural networks obtained are able to generate the Pareto set, from which a model with the smallest validation error is selected.

Like what you’re reading?

Already a member?

Get this article FREE with a new membership!

Improved clustered hierarchical tandem system with bottom-up processing
Acoustics, Speech, and Signal Processing, IEEE International Conference on
Genetic Algorithms for Bi-Objective Job Shop Scheduling Problem
Hybrid Intelligent Systems, International Conference on
Combined multi-layer perceptron neural network and sliding mode technique for parallel robots control : An adaptive approach
Neural Networks, IEEE - INNS - ENNS International Joint Conference on
Neural network based secure media access control protocol for wireless sensor networks
Neural Networks, IEEE - INNS - ENNS International Joint Conference on
Hierarchical tandem feature extraction
Proceedings of International Conference on Acoustics, Speech and Signal Processing (CASSP'02)
A comparative study of signal representations and classification techniques for speech recognition
Acoustics, Speech, and Signal Processing, IEEE International Conference on
Improving Backpropagation with Sliding Mode Control
Neural Networks, Brazilian Symposium on
Performance Comparison of Different Multilayer Perceptron Network Activation Functions in Automated Weather Classification
Asia International Conference on Modelling & Simulation
Reference Line Guided Pareto Local Search for Bi-Objective Traveling Salesman Problem
2017 IEEE International Conference on Computational Science and Engineering (CSE) and IEEE International Conference on Embedded and Ubiquitous Computing (EUC)
A Bi-Objective Approach for Product Recommendations
2019 IEEE International Conference on Big Data (Big Data)

Control of Generalization with a Bi-Objective Sliding Mode Control Algorithm

Authors

Abstract

Related Articles