Robust stabilization for the nonlinear benchmark problem (TORA) using neural nets and evolution strategies

2007 ◽  
pp. 301-313
Author(s):  
Cesáreo Raimúndez
Keyword(s):  
Robust Stabilization ◽  
Neural Nets ◽  
Evolution Strategies ◽  
Benchmark Problem

Feature Extraction Through LOCOCODE

1999 ◽  
Vol 11 (3) ◽  
pp. 679-714 ◽  
Author(s):  
Sepp Hochreiter ◽  
Jürgen Schmidhuber
Keyword(s):  
Unsupervised Learning ◽  
Principal Component ◽  
Low Complexity ◽  
Component Analysis ◽  
Classification Performance ◽  
Neural Nets ◽  
Benchmark Problem ◽  
Code Generator ◽  
Feature Detectors ◽  
Novel Approach

Low-complexity coding and decoding (LOCOCODE) is a novel approach to sensory coding and unsupervised learning. Unlike previous methods, it explicitly takes into account the information-theoretic complexity of the code generator. It computes lococodes that convey information about the input data and can be computed and decoded by low-complexity mappings. We implement LOCOCODE by training autoassociators with flat minimum search, a recent, general method for discovering low-complexity neural nets. It turns out that this approach can unmix an unknown number of independent data sources by extracting a minimal number of low-complexity features necessary for representing the data. Experiments show that unlike codes obtained with standard autoencoders, lococodes are based on feature detectors, never unstructured, usually sparse, and sometimes factorial or local (depending on statistical properties of the data). Although LOCOCODE is not explicitly designed to enforce sparse or factorial codes, it extracts optimal codes for difficult versions of the “bars” benchmark problem, whereas independent component analysis (ICA) and principal component analysis (PCA) do not. It produces familiar, biologically plausible feature detectors when applied to real-world images and codes with fewer bits per pixel than ICA and PCA. Unlike ICA, it does not need to know the number of independent sources. As a preprocessor for a vowel recognition benchmark problem, it sets the stage for excellent classification performance. Our results reveal an interesting, previously ignored connection between two important fields: regularizer research and ICA-related research. They may represent a first step toward unification of regularization and unsupervised learning.

Generalized KYP Synthesis on the Phase Stabilization and Gain Stabilization Compensators for the HDD Benchmark Problem

2017 ◽  
Vol 137 (4) ◽  
pp. 342-349 ◽  
Author(s):  
Masato Kanematsu ◽  
Hiroshi Fujimoto
Keyword(s):  
Benchmark Problem ◽  
Phase Stabilization

Robust Stabilization and Evaluation of the Weighted Suppression of Disturbances in Control Systems

2016 ◽  
Vol 48 (11) ◽  
pp. 54-67
Author(s):  
Alexey G. Mazko ◽  
Sergey N. Kusii
Keyword(s):  
Control Systems ◽  
Robust Stabilization

Robust Stabilization of Marine Mobile Objects on the Basis of Systems with Variable Structure of Feedbacks

2011 ◽  
Vol 43 (6) ◽  
pp. 16-29 ◽  
Author(s):  
Victor L. Timchenko ◽  
Yuriy P. Kondratenko
Keyword(s):  
Robust Stabilization ◽  
Variable Structure ◽  
Mobile Objects

Application of a Game Theoretic Controller to a Benchmark Problem

1990 ◽  
Author(s):  
Ihnseok Rhee ◽  
Jason L. Speyer
Keyword(s):  
Benchmark Problem ◽  
Game Theoretic

The Application of Cost Averaging Techniques to Robust Control of the Benchmark Problem

1991 ◽  
Author(s):  
Nesbitt W. Hagood ◽  
Edward F. Crawley
Keyword(s):  
Robust Control ◽  
Benchmark Problem ◽  
Averaging Techniques

Robust Stabilization With Positive Real Uncertainty

1991 ◽  
Author(s):  
Waesim M. Haddad ◽  
Dennis S. Bernstein
Keyword(s):  
Robust Stabilization ◽  
Positive Real

Stochastic Robustness Synthesis for a Benchmark Problem

1992 ◽  
Author(s):  
Robert F. Stengel ◽  
Christopher I. Marrison
Keyword(s):  
Benchmark Problem
Sign in / Sign up

Export Citation Format

Share Document