Search results for "Neural"
showing 10 items of 2783 documents
A New Min-Max Optimisation Approach for Fast Learning Convergence of Feed-Forward Neural Networks
1993
One of the most critical aspect for a wide use of neural networks to real world problems is related to the learning process which is known to be computational expensive and time consuming.
Conflict resolution in the multi-stakeholder stepped spillway design under uncertainty by machine learning techniques
2021
Abstract The optimal spillway design is of great significance since these structures can reduce erosion downstream of the dams. This study proposes a risk-based optimization framework for a stepped spillway to achieve an economical design scenario with the minimum loss in hydraulic performance. Accordingly, the stepped spillway was simulated in the FLOW-3D® model, and the validated model was repeatedly performed for various geometric states. The results were used to form a Multilayer Perceptron artificial neural network (MLP-ANN) surrogate model. Then, a risk-based optimization model was formed by coupling the MLP-ANN and NSGA-II. The concept of conditional value at risk (CVaR) was utilized…
AMaLGaM IDEAs in noiseless black-box optimization benchmarking
2009
This paper describes the application of a Gaussian Estimation-of-Distribution (EDA) for real-valued optimization to the noiseless part of a benchmark introduced in 2009 called BBOB (Black-Box Optimization Benchmarking). Specifically, the EDA considered here is the recently introduced parameter-free version of the Adapted Maximum-Likelihood Gaussian Model Iterated Density-Estimation Evolutionary Algorithm (AMaLGaM-IDEA). Also the version with incremental model building (iAMaLGaM-IDEA) is considered.
A hybrid metaheuristic for the cyclic antibandwidth problem
2013
We propose a hybrid artificial bee colony algorithm for the cyclic antibandwidth problem.We present a computational comparison of different parameter settings.We derive a fine-tuning hybrid artificial bee colony algorithm.The proposal is very competitive with the state-of-the-art algorithm for the cyclic antibandwidth problem. In this paper, we propose a hybrid metaheuristic algorithm to solve the cyclic antibandwidth problem. This hard optimization problem consists of embedding an n-vertex graph into the cycle Cn, such that the minimum distance (measured in the cycle) of adjacent vertices is maximized. It constitutes a natural extension of the well-known antibandwidth problem, and can be v…
Path relinking and GRG for artificial neural networks
2006
Artificial neural networks (ANN) have been widely used for both classification and prediction. This paper is focused on the prediction problem in which an unknown function is approximated. ANNs can be viewed as models of real systems, built by tuning parameters known as weights. In training the net, the problem is to find the weights that optimize its performance (i.e., to minimize the error over the training set). Although the most popular method for training these networks is back propagation, other optimization methods such as tabu search or scatter search have been successfully applied to solve this problem. In this paper we propose a path relinking implementation to solve the neural ne…
Hydropower Optimization Using Deep Learning
2019
This paper demonstrates how deep learning can be used to find optimal reservoir operating policies in hydropower river systems. The method that we propose is based on the implicit stochastic optimization (ISO) framework, using direct policy search methods combined with deep neural networks (DNN). The findings from a real-world two-reservoir hydropower system in southern Norway suggest that DNNs can learn how to map input (price, inflow, starting reservoir levels) to the optimal production pattern directly. Due to the speed of evaluating the DNN, this approach is from an operational standpoint computationally inexpensive and may potentially address the long-standing problem of high dimension…
Memetic Variation Local Search vs. Life-Time Learning in Electrical Impedance Tomography
2009
In this article, various metaheuristics for a numerical optimization problem with application to Electric Impedance Tomography are tested and compared. The experimental setup is composed of a real valued Genetic Algorithm, the Differential Evolution, a self adaptive Differential Evolution recently proposed in literature, and two novel Memetic Algorithms designed for the problem under study. The two proposed algorithms employ different algorithmic philosophies in the field of Memetic Computing. The first algorithm integrates a local search into the operations of the offspring generation, while the second algorithm applies a local search to individuals already generated in the spirit of life-…
A novel abstraction for swarm intelligence: particle field optimization
2016
Particle swarm optimization (PSO) is a popular meta-heuristic for black-box optimization. In essence, within this paradigm, the system is fully defined by a swarm of "particles" each characterized by a set of features such as its position, velocity and acceleration. The consequent optimized global best solution is obtained by comparing the personal best solutions of the entire swarm. Many variations and extensions of PSO have been developed since its creation in 1995, and the algorithm remains a popular topic of research. In this work we submit a new, abstracted perspective of the PSO system, where we attempt to move away from the swarm of individual particles, but rather characterize each …
Decision Making on Pareto Front Approximations with Inherent Nondominance
2011
t Approximating the Pareto fronts of nonlinear multiobjective optimization problems is considered and a property called inherent nondominance is proposed for such approximations. It is shown that an approximation having the above property can be explored by interactively solving a multiobjective optimization problem related to it. This exploration can be performed with available interactive multiobjective optimization methods. The ideas presented are especially useful in solving computationally expensive multiobjective optimization problems with costly function value evaluations. peerReviewed
Analysis of human skin hyper-spectral images by non-negative matrix factorization
2011
International audience; This article presents the use of Non-negative Matrix Factorization, a blind source separation algorithm, for the decomposition of human skin absorption spectra in its main pigments: melanin and hemoglobin. The evaluated spectra come from a Hyper-Spectral Image, which is the result of the processing of a Multi-Spectral Image by a neural network-based algorithm. The implemented source separation algorithm is based on a multiplicative coeffi cient upload. The goal is to represent a given spectrum as the weighted sum of two spectral components. The resulting weighted coefficients are used to quantify melanin and hemoglobin content in the given spectra. Results present a …