Current Issue : October - December Volume : 2013 Issue Number : 4 Articles : 6 Articles
We have shown how the nine tiles in the projection-based model for cardinal directions can be partitioned into sets based on\r\nhorizontal and vertical constraints (called Horizontal and Vertical Constraints Model) in our previous papers (Kor and Bennett,\r\n2003 and 2010). In order to come up with an expressive hybrid model for direction relations between two-dimensional singlepiece\r\nregions (without holes), we integrate the well-known RCC-8 model with the above-mentioned model. From this expressive\r\nhybrid model, we derive 8 basic binary relations and 13 feasible as well as jointly exhaustive relations for the x- and y-directions,\r\nrespectively. Based on these basic binary relations, we derive two separate 8 Ã?â?? 8 composition tables for both the expressive and\r\nweak direction relations.We introduce a formula that can be used for the computation of the composition of expressive and weak\r\ndirection relations between ââ?¬Å?whole or partââ?¬Â regions. Lastly, we also show how the expressive hybrid model can be used to make\r\nseveral existential inferences that are not possible for existing models....
Echo state networks are a relatively new type of recurrent neural networks that have shown great potentials for solving nonlinear,\r\ntemporal problems. The basic idea is to transform the low dimensional temporal input into a higher dimensional state,\r\nand then train the output connection weights to make the system output the target information. Because only the output weights\r\nare altered, training is typically quick and computationally efficient compared to training of other recurrent neural networks. This\r\npaper investigates using an echo state network to learn the inverse kinematics model of a robot simulator with feedback-errorlearning.\r\nIn this scheme teacher forcing is not perfect, and joint constraints on the simulator makes the feedback error inaccurate.\r\nA novel trainingmethod which is less influenced by the noise in the training data is proposed and compared to the traditional ESN\r\ntraining method....
We introduce a reinforcement learning architecture designed for problems with an infinite number of states, where each state can\r\nbe seen as a vector of real numbers and with a finite number of actions, where each action requires a vector of real numbers as\r\nparameters. The main objective of this architecture is to distribute in two actors the work required to learn the final policy. One\r\nactor decideswhat actionmust be performed; meanwhile, a second actor determines the right parameters for the selected action.We\r\ntested our architecture and one algorithmbased on it solving the robot dribbling problem, a challenging robot control problem taken\r\nfrom the RoboCup competitions. Our experimental work with three different function approximators provides enough evidence\r\nto prove that the proposed architecture can be used to implement fast, robust, and reliable reinforcement learning algorithms...
Artificial intelligence (AI) systems are widely used in all types of chemical industries. It is accepted as a technology offering an alternative way to tackle complex and will defined problems. They have been used in diverse applications control, robotics, pattern recognition, forecasting, medicine, power systems, manufacturing, optimization, signal processing, and social/psychological sciences. The major objective of this paper is to illustrate how AI techniques might play an important role in chemical industries and prediction of the process. The paper illustrates the improvement of artificial intelligence in various process industries. Computational fluid dynamics (CFD), Fuzzy logic (FL), Artificial neural network (ANN) are some simulation tools, which uses powerful computer and applied mathematics to model and optimal design in industrial processes. Apart from various industries, different types of unit operations were compared in this paper. Settling process, drying, painting, fermentation processes are explained in with respect artificial intelligence....
?is paper presents an approach to the study of switching overvoltages during power equipment energization. Switching action is\none of the most important issues in the power system restoration schemes. ?is action may lead to overvoltages which can damage\nsome equipment and delay power system restoration. In this work, switching overvoltages caused by power equipment energization\nare evaluated using arti??cial-neural-network- (ANN-) based approach. Both multilayer perceptron (MLP) trained with Levenberg-\nMarquardt (LM) algorithm and radial basis function (RBF) structure have been analyzed. In the cases of transformer and shunt\nreactor energization, the worst case of switching angle and remanent ??ux has been considered to reduce the number of required\nsimulations for training ANN. Also, for achieving good generalization capability for developed ANN, equivalent parameters of the\nnetwork are used as ANN inputs. Developed ANN is tested for a partial of 39-bus New England test system, and results show the\neffectiveness of the proposed method to evaluate switching overvoltages....
This research explores the relation between environmental structure and neurocognitive structure. We hypothesize that selection\r\npressure on abilities for efficient learning (especially in settings with limited or no reward information) translates into selection\r\npressure on correspondence relations between neurocognitive and environmental structure, since such correspondence allows for\r\nsimple changes in the environment to be handled with simple learning updates in neurocognitive structure.We present a model in\r\nwhich a simple formof reinforcement-free learning is evolved in neural networks using neuromodulation and analyze the effect this\r\nselection for learning ability has on the virtual species� neural organization.We find a higher degree of organization than in a control\r\npopulation evolved without learning ability and discuss the relation between the observed neural structure and the environmental\r\nstructure.We discuss our findings in the context of the environmental complexity thesis, the Baldwin effect, and other interactions\r\nbetween adaptation processes....
Loading....