Serwis Infona wykorzystuje pliki cookies (ciasteczka). Są to wartości tekstowe, zapamiętywane przez przeglądarkę na urządzeniu użytkownika. Nasz serwis ma dostęp do tych wartości oraz wykorzystuje je do zapamiętania danych dotyczących użytkownika, takich jak np. ustawienia (typu widok ekranu, wybór języka interfejsu), zapamiętanie zalogowania. Korzystanie z serwisu Infona oznacza zgodę na zapis informacji i ich wykorzystanie dla celów korzytania z serwisu. Więcej informacji można znaleźć w Polityce prywatności oraz Regulaminie serwisu. Zamknięcie tego okienka potwierdza zapoznanie się z informacją o plikach cookies, akceptację polityki prywatności i regulaminu oraz sposobu wykorzystywania plików cookies w serwisie. Możesz zmienić ustawienia obsługi cookies w swojej przeglądarce.
Here I apply three reinforcement learning methods to the full, continuous action, swing-up acrobot control benchmark problem. These include two approaches from the literature: CACLA and NM-SARSA and a novel approach which I refer to as Nelder Mead-SARSA. Nelder Mead-SARSA, like NMSARSA, directly optimises the state-action value function for action selection, in order to allow continuous action reinforcement...
To describe the approach of real-world activities we have proposed an idea of SLNA algorithm and its diagram. In this paper we are using supervised learning to train the network. In supervised learning desire response is provided by the teacher in correspondence to the particular input. To explain the concept of SLNNA algorithm we have used a real-world example of travel agency (make my trip agency)...
This paper presents a new procedure for identification of multiple cracks in beam. Natural frequency is frequently used as a parameter for detection of cracks in the structures. The process of crack identification in presented procedure is consists of four stages. In first stage, three natural frequencies of a cantilever beam for different locations and depths of cracks were obtained using Finite...
Out of several antenna design techniques the Artificial Neural Network (ANN) based method is suitable for prediction of characteristic parameters of loop antenna by considering transmit - receive conditions of practical communication set-ups. The predicted set of parameters can be used to fix dimensions of a loop antenna which involves theoretical calculations. This work proposes an approach to determine...
Normalized radial basis function (NRBF) neural network is presented to directly approach the Q-value function and generalize the information learnt by learning agent in continuous space. The action which impacts on environment is the one with maximum output of NRBF in the current state, and generated through Quantum-Behaved Particle Swarm Optimizer based on the current state. The effectiveness of...
Under real and continuously improving manufacturing conditions, lithography hotspot detection faces several key challenges. First, real hotspots become less but harder to fix at post-layout stages; second, false alarm rate must be kept low to avoid excessive and expensive post-processing hotspot removal; third, full chip physical verification and optimization require fast turn-around time. To address...
This paper presents an optimizing methodology for implementing a multi-layer perceptron (MLP) neural network in a Field Programmable Gate Array (FPGA) device. In order to obtain an efficient implementation, a compromise of time and area is needed. Starting from simulation in the learning phase with fixed point operators, we have developed a methodology which allows the automatic generation of a VHDL...
This paper presents a novel algorithm for multiobjective training of Radial Basis Function (RBF) networks based on least-squares and Particle Swarm Optimization methods. The formulation is based on the fundamental concept that supervised learning is a bi-objective optimization problem, in which two conflicting objectives should be minimized. The objectives are related to the empirical training error...
The emerging computational grid infrastructure consists of widely distributed heterogeneous resources, which makes mapping of increasingly complex applications a very challenging task. Utility Management Systems (UMS) manage large number of workflows with high resource requirements and thereby optimization of resource utilization has to be adapted. In this work we propose the architecture that implements...
A common drawback of standard reinforcement learning algorithms is their inability to scale-up to real-world problems. For this reason, a current important trend of research is (state-action) value function approximation. A prominent value function approximator is the least-squares temporal differences (LSTD) algorithm. However, for technical reasons, linearity is mandatory: the parameterization of...
Since the excellent performances of treating nonlinear data with self-learning capability, the neural networks (NNs) are wildly use in financial prediction problem. But the NNs more or less suffer from the slow convergence, “black-box” i.e., it is almost impossible to analysis them for how they work. The Fuzzy Neural Networks(FNN) allow to add rules to neural networks. This avoids the black-box but...
The problem of construction the neuronetworking systems for non-stationary information adaptive processing at various practical applications is formulated. The developed methods and algorithms of neural network training subset formation allow to take into account the conditions of information transfer, variation of statistical parameters and dynamic properties of data. The controlling algorithms which...
This paper proposes a recurrent neural fuzzy network with the reinforcement improved particle swarm optimization (R-IPSO) for solving various control problems. The R-IPSO, which consists of structure learning and parameter learning, is also proposed. The structure learning is adopts several sub-swarms to constitute variable fuzzy systems and uses an elite-based structure strategy (ESS) to find suitable...
This paper deals with time-optimization of trajectories of wheeled robots within the speed and other constraints. The cubic Hermite spline curve with the method of speed profile computation is used to determine the trajectory. This method is summarized and extended to allow the optimization with the described constraints. It ensures fulfilment of required initial parameters of motion. The parameters...
In the paper, a novel hybrid algorithm based on Baldwinian learning and PSO (BLPSO) is proposed to increase the diversity of the particles and to prevent premature convergence of PSO. Firstly, BLPSO adopts the Baldwinian operator to simulate the learning mechanism among the particles and employs the information of the swarm to alter the search space adaptively. Secondly, a mutation operation is introduced...
Extension neural network is a new method based on Extenics and neural networks, it is full use of the Extension of qualitative and quantitative description of the advantages, but also consider the parallel structure characteristics, of neural network. This article describes the extension theory and neural network fusion extension neural network structure and introduce ENN algorithm based on genetic...
Cooperative approaches have proved to be very useful in evolutionary computation. This paper a novel multi-swarm cooperative particle swarm optimization (PSO) is proposed. It involves a collection of two sub-swarms that interact by exchanging information to solve a problem. The two swarms execute IPSO (improved PSO) independently to maintain the diversity of populations, while introducing extremal...
Ensemble learning is a method to improve the performance of classification and prediction algorithms. It has received considerable attention because of its prominent generalization and performance improvement. However, its performance can be degraded due to multicollinearity problem where multiple classifiers of an ensemble are highly correlated with. This paper proposes genetic algorithm-based coverage...
In this paper, we propose a cooperative learning algorithm for Multi-category classification which is decomposed into two sub-optimization problems by using the support vector machine technique. The proposed cooperative learning algorithm consists of two single learning algorithms and each sub-optimization problem is solved by one of them. Unlike the cooperative neural network, the proposed cooperative...
A key feature in population based optimization algorithms is the ability to explore a search space and make a decision based on multiple solutions. In this paper, an incremental learning strategy based on a dynamic particle swarm optimization (DPSO) algorithm allows to produce heterogeneous ensembles of classifiers for video-based face recognition. This strategy is applied to an adaptive classification...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.