Search results for "Function approximation"

A survey on handling computationally expensive multiobjective optimization problems with evolutionary algorithms

2017

Evolutionary algorithms are widely used for solving multiobjective optimization problems but are often criticized because of a large number of function evaluations needed. Approximations, especially function approximations, also referred to as surrogates or metamodels are commonly used in the literature to reduce the computation time. This paper presents a survey of 45 different recent algorithms proposed in the literature between 2008 and 2016 to handle computationally expensive multiobjective optimization problems. Several algorithms are discussed based on what kind of an approximation such as problem, function or fitness approximation they use. Most emphasis is given to function approxim…

Determining the Parameters of a Sugeno Fuzzy Controller Using a Parallel Genetic Algorithm

2013

Developed in the mid 1970s, the technique based on genetic algorithms proved its usefulness in finding optimal or near optimal solutions to problems for which accurate solving strategies are either non-existent or require excessively long running time. We implemented a genetic algorithm to determine the parameters of a Sugeno fuzzy controller for the Truck Backer-Upper problem (This problem is considered an acknowledged benchmark in nonlinear system identification.). Less known at first than Mamdami fuzzy controllers, Sugeno fuzzy controllers became popular once they were included into the ANFIS neuro-fuzzy Matlab library. By their nature, Sugeno controllers can be regarded as interpolation…

Real-time clothoid approximation by Rational Bezier curves

2008

This paper presents a novel technique for implementing Clothoidal real-time paths for mobile robots. As first step, rational Bezier curves are obtained as approximation of the Fresnel integrals. By rescaling, rotating and translating the previously computed RBC, an on-line Clothoidal path is obtained. In this process, coefficients, weights and control points are kept invariant. This on-line approach guarantees that an RBC has the same behavior as the original Clothoid using a low curve order. The resulting Clothoidal path allows any two arbitrary poses to be joined in a plane. RBCs working as Clothoids are also used to search for the shortest bounded-curvature path with a significant comput…

Assigning discounts in a marketing campaign by using reinforcement learning and neural networks

2009

In this work, RL is used to find an optimal policy for a marketing campaign. Data show a complex characterization of state and action spaces. Two approaches are proposed to circumvent this problem. The first approach is based on the self-organizing map (SOM), which is used to aggregate states. The second approach uses a multilayer perceptron (MLP) to carry out a regression of the action-value function. The results indicate that both approaches can improve a targeted marketing campaign. Moreover, the SOM approach allows an intuitive interpretation of the results, and the MLP approach yields robust results with generalization capabilities.

Emergent Collective Behaviors in a Multi-agent Reinforcement Learning Pedestrian Simulation: A Case Study

2015

In this work, a Multi-agent Reinforcement Learning framework is used to generate simulations of virtual pedestrians groups. The aim is to study the influence of two different learning approaches in the quality of generated simulations. The case of study consists on the simulation of the crossing of two groups of embodied virtual agents inside a narrow corridor. This scenario is a classic experiment inside the pedestrian modeling area, because a collective behavior, specifically the lanes formation, emerges with real pedestrians. The paper studies the influence of different learning algorithms, function approximation approaches, and knowledge transfer mechanisms on performance of learned ped…

A Survey on Gaussian Processes for Earth-Observation Data Analysis: A Comprehensive Investigation

2016

Gaussian processes (GPs) have experienced tremendous success in biogeophysical parameter retrieval in the last few years. GPs constitute a solid Bayesian framework to consistently formulate many function approximation problems. This article reviews the main theoretical GP developments in the field, considering new algorithms that respect signal and noise characteristics, extract knowledge via automatic relevance kernels to yield feature rankings automatically, and allow applicability of associated uncertainty intervals to transport GP models in space and time that can be used to uncover causal relations between variables and can encode physically meaningful prior knowledge via radiative tra…

Learning Structures in Earth Observation Data with Gaussian Processes

2020

Gaussian Processes (GPs) has experienced tremendous success in geoscience in general and for bio-geophysical parameter retrieval in the last years. GPs constitute a solid Bayesian framework to formulate many function approximation problems consistently. This paper reviews the main theoretical GP developments in the field. We review new algorithms that respect the signal and noise characteristics, that provide feature rankings automatically, and that allow applicability of associated uncertainty intervals to transport GP models in space and time. All these developments are illustrated in the field of geoscience and remote sensing at a local and global scales through a set of illustrative exa…

On the Consistency Restoring in SPH

2009

Flavor Release from i-Carrageenan Matrix: A Quantitative Structure-Property Relationships Approach

2006

International audience; We carried out a QSPR (quantitative structure-property relationships) approach to evaluate the influence of the chemical structure of aqueous matrixes over the partition coefficient between the gas phase and the matrix. The determination of the partition coefficient of flavor ingredients was performed by headspace analysis at equilibrium for both saline solution and -carrageenan gel. Starting from an initial list of 90 descriptors, we selected 10 descriptors to perform equation generation by the GFA (genetic function approximation) method available in the Cerius2 package. The best obtained equations involve only five descriptors, which encode electronic properties of…

Enabling XCSF to cope with dynamic environments via an adaptive error threshold

2020

The learning classifier system XCSF is a variant of XCS employed for function approximation. Although XCSF is a promising candidate for deployment in autonomous systems, its parameter dependability imposes a significant hurdle, as a-priori parameter optimization is not feasible for complex and changing environmental conditions. One of the most important parameters is the error threshold, which can be interpreted as a target bound on the approximation error and has to be set according to the approximated function. To enable XCSF to reliably approximate functions that change during runtime, we propose the use of an error threshold, which is adapted at run-time based on the currently achieved …