The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
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...
In this paper, we investigate the machine learning based strategies for dynamic channel selection in Cognitive Access Points (CogAPs) of WLANs. We employ Multi-layer Feedforward Neural Network (MFNN) models that utilize historical traffic information from network environment for learning the influence of spatio-temporal-spectral factors on the network and then predicting future traffic loads on each...
This paper implements a speed/current control of a prototype series DC motor using a buck converter model. It first came up with, a performance analysis for current and speed controllers are provided followed by a simulation in MATLAB. Analyzing the discontinuous conduction mode (DCM) of the buck converter along with the non-linear behavior of the mechanical load put us forward to an efficient strategy...
Decentralized scheduling with dispatching rules is applied in many fields of logistics and production, especially in semiconductor manufacturing, which is characterized by high complexity and dynamics. Many dispatching rules have been found, which perform well on different scenarios, however no rule has been found, which outperforms other rules across various objectives. To tackle this drawback, approaches,...
Supervised learning of voting automata for the surgeon's right hand motion recognition constitutes the main result reported in the present paper. Within the framework of the project, aiming the design of scrub nurse robot a number of methods for recognizing the current stage of the surgery has been developed. Obviously no one of the methods separately can guarantee hundred percent correct recognition...
A challenge in designing a RF MEMS switch is the determination of its parameters to satisfy the application requirements. Often this is done through a set of comprehensive time consuming simulations. This paper employs neural networks and develops a supervised learner that is capable of determining S11 parameter for a RF MEMS shunt switch. The inputs are the length its L and the height of its gap...
Fast convergence-rate, low computation complexity and good stability are important goals in the researching area of neural network learning algorithm. A kind of parallel computing lagged-start hybrid optimization algorithm is studied, it not only integrates the basic gradient method and the unconstrained optimization algorithm to realize the supplement of their advantages, but also makes full use...
During early stage of primary restoration process, unexpected Overvoltages may happen due to nonlinear interaction between the unloaded transformer and the transmission system. The most effective method for the limitation of the switching overvoltages is controlled switching since the magnitudes of the produced transients are strongly dependent on the closing instants of the switch. We introduce a...
Sliding mode control (SMC) of cleaning robot's mobile manipulator based on neural networks which have nonlinear approximation ability is put forward in this article. The controller reduces inherent chattering phenomenon sharply when the uncertainties and external disturbances are unknown. Structure of sliding mode control and neural networkspsila learning algorithms using Lyapunov theorem are designed...
To compensate voltage difference between the reference and the actual output voltages caused by dead-time effects, a novel compensation method for permanent magnet synchronous motor (PMSM) drive based on neuro-fuzzy observer is proposed. This method presents the implementation of a voltage distortion observer based on the artificial neural network (ANN), using the output of the fuzzy controller (FC),...
This paper presents an application of neural network interleaved training algorithm proposed in in the domain of chess. In order to use the referenced learning method a structure of metric space is introduced in the space of chess moves. Neural network is used as a classifier of a distance from a given move to the optimal one, leading to significant limitation of the set of moves potentially worth...
We present the memetic climber, a simple search algorithm that learns topology and weights of neural networks on different time scales. When applied to the problem of learning control for a simulated racing task with carefully selected inputs to the neural network, the memetic climber outperforms a standard hill-climber. When inputs to the network are less carefully selected, the difference is drastic...
Q-Learning can successfully solve the congestion problem of isolated intersection. But it is not available to realize the coordination between two intersections. A switching-model of two intersections is introduced in this paper. The concept of combinative phase is put forward in order to divert two intersections into a single one. In this way, we can apply Q-Learning on two adjacent intersections...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.