The Experts below are selected from a list of 3867 Experts worldwide ranked by ideXlab platform
George D. C. Cavalcanti - One of the best experts on this subject based on the ideXlab platform.
-
IJCNN - Diversity in Task Decomposition: A strategy for combining mixtures of experts
The 2013 International Joint Conference on Neural Networks (IJCNN), 2013Co-Authors: Everson Veríssimo, Diogo Da Silva Severo, George D. C. CavalcantiAbstract:The “no free lunch” theorem has stated that learning algorithms cannot be universally good. An alternative to alleviate the weakness of using only one classifier is to combine several of them. Mixture of Experts is a learning algorithm that combines classifiers, in which each classifier or expert is dedicated to solve part of the problem. The partition of the problem is defined by a step called Task Decomposition where the problem is divided in subproblems. This paper proposes an approach to combine mixture of experts, in which different Task Decomposition methods are used to divide the problem. This strategy aims to increase the diversity of the ensemble, since different Task Decomposition methods generate different partitions of the database. The experimental study shows that the proposed method obtains better accuracy rates when compared with the traditional mixture of experts.
-
Diversity in Task Decomposition: A strategy for combining mixtures of experts
The 2013 International Joint Conference on Neural Networks (IJCNN), 2013Co-Authors: Everson Veríssimo, George D. C. Cavalcanti, Diogo Da Silva Severo, Tsang Ing RenAbstract:The “no free lunch” theorem has stated that learning algorithms cannot be universally good. An alternative to alleviate the weakness of using only one classifier is to combine several of them. Mixture of Experts is a learning algorithm that combines classifiers, in which each classifier or expert is dedicated to solve part of the problem. The partition of the problem is defined by a step called Task Decomposition where the problem is divided in subproblems. This paper proposes an approach to combine mixture of experts, in which different Task Decomposition methods are used to divide the problem. This strategy aims to increase the diversity of the ensemble, since different Task Decomposition methods generate different partitions of the database. The experimental study shows that the proposed method obtains better accuracy rates when compared with the traditional mixture of experts.
-
A nonexclusive Task Decomposition method for modular neural networks
The 2010 International Joint Conference on Neural Networks (IJCNN), 2010Co-Authors: Victor M. O. Alves, George D. C. CavalcantiAbstract:Modular neural networks (MNNs) architectures have been developed aiming to outperform single neural nets. One of the main drawbacks in the construction of the MNNs is the Task Decomposition which consists in divide the problem into simpler sub-problems. This paper proposes a novel Task Decomposition method in which the classes of the problem can be divided redundantly. Thus, two different expert modules can have the same class. This is specially interesting for problems that have multimodal classes. The proposed MNN, called Redundant Pattern Distributor, is compared with other ones over many databases and the results show its effectiveness.
-
IJCNN - A nonexclusive Task Decomposition method for modular neural networks
The 2010 International Joint Conference on Neural Networks (IJCNN), 2010Co-Authors: Victor M. O. Alves, George D. C. CavalcantiAbstract:Modular neural networks (MNNs) architectures have been developed aiming to outperform single neural nets. One of the main drawbacks in the construction of the MNNs is the Task Decomposition which consists in divide the problem into simpler sub-problems. This paper proposes a novel Task Decomposition method in which the classes of the problem can be divided redundantly. Thus, two different expert modules can have the same class. This is specially interesting for problems that have multimodal classes. The proposed MNN, called Redundant Pattern Distributor, is compared with other ones over many databases and the results show its effectiveness.
-
Tree Architecture Pattern Distributor: a Task Decomposition classification approach
2009 International Joint Conference on Neural Networks, 2009Co-Authors: Victor M. O. Alves, George D. C. CavalcantiAbstract:Task Decomposition is a widely used method to solve complex and large problems. In this paper, it is proposed a novel Task Decomposition approach, named tree architecture pattern distributor (TreeArchPD), which is based on another Task Decomposition technique, called pattern distributor. The main idea is to design a tree architecture with many distributors instead of using only one distributor as proposed by the original technique. It is also proposed a new class grouping method that aims to optimize the class selection for Task Decomposition. Many experiments were done and they showed the effectiveness of the proposed approaches.
Victor M. O. Alves - One of the best experts on this subject based on the ideXlab platform.
-
A nonexclusive Task Decomposition method for modular neural networks
The 2010 International Joint Conference on Neural Networks (IJCNN), 2010Co-Authors: Victor M. O. Alves, George D. C. CavalcantiAbstract:Modular neural networks (MNNs) architectures have been developed aiming to outperform single neural nets. One of the main drawbacks in the construction of the MNNs is the Task Decomposition which consists in divide the problem into simpler sub-problems. This paper proposes a novel Task Decomposition method in which the classes of the problem can be divided redundantly. Thus, two different expert modules can have the same class. This is specially interesting for problems that have multimodal classes. The proposed MNN, called Redundant Pattern Distributor, is compared with other ones over many databases and the results show its effectiveness.
-
IJCNN - A nonexclusive Task Decomposition method for modular neural networks
The 2010 International Joint Conference on Neural Networks (IJCNN), 2010Co-Authors: Victor M. O. Alves, George D. C. CavalcantiAbstract:Modular neural networks (MNNs) architectures have been developed aiming to outperform single neural nets. One of the main drawbacks in the construction of the MNNs is the Task Decomposition which consists in divide the problem into simpler sub-problems. This paper proposes a novel Task Decomposition method in which the classes of the problem can be divided redundantly. Thus, two different expert modules can have the same class. This is specially interesting for problems that have multimodal classes. The proposed MNN, called Redundant Pattern Distributor, is compared with other ones over many databases and the results show its effectiveness.
-
Tree Architecture Pattern Distributor: a Task Decomposition classification approach
2009 International Joint Conference on Neural Networks, 2009Co-Authors: Victor M. O. Alves, George D. C. CavalcantiAbstract:Task Decomposition is a widely used method to solve complex and large problems. In this paper, it is proposed a novel Task Decomposition approach, named tree architecture pattern distributor (TreeArchPD), which is based on another Task Decomposition technique, called pattern distributor. The main idea is to design a tree architecture with many distributors instead of using only one distributor as proposed by the original technique. It is also proposed a new class grouping method that aims to optimize the class selection for Task Decomposition. Many experiments were done and they showed the effectiveness of the proposed approaches.
-
IJCNN - Tree Architecture Pattern Distributor: a Task Decomposition classification approach
2009 International Joint Conference on Neural Networks, 2009Co-Authors: Victor M. O. Alves, George D. C. CavalcantiAbstract:Task Decomposition is a widely used method to solve complex and large problems. In this paper, it is proposed a novel Task Decomposition approach, named Tree Architecture Pattern Distributor (TreeArchPD), which is based on another Task Decomposition technique, called Pattern Distributor. The main idea is to design a tree architecture with many Distributors instead of using only one Distributor as proposed by the original technique. It is also proposed a new class grouping method that aims to optimize the class selection for Task Decomposition. Many experiments were done and they showed the effectiveness of the proposed approaches.
Yi Fei Zheng - One of the best experts on this subject based on the ideXlab platform.
-
Task Decomposition for a multilimbed robot to work in reachable but unorientable space
IEEE Transactions on Robotics and Automation, 1991Co-Authors: Chau Su, Yi Fei ZhengAbstract:Robot manipulators installed on legged mobile platforms are suggested for enlarging robot workspace. To plan the motion of such a system, the arm-platform motion coordination problem is raised, and a Task Decomposition is proposed to solve the problem. A given Task described by the destination position and orientation of the end effector is decomposed into subTasks for arm manipulation and for platform configuration, respectively. The former is defined as the end-effector position and orientation with respect to the platform, and the latter as the platform position and orientation in the base coordinates. Three approaches are proposed for the Task Decomposition. The approaches are also evaluated in terms of the displacements, from which an optimal approach can be selected
-
Task Decomposition for multilimbed robots to work in the reachable-but-unorientable space
Proceedings. IEEE International Conference on Robotics and Automation, 1990Co-Authors: Chau Su, Yi Fei ZhengAbstract:Multilimbed industrial robots that have at least one arm and two or more legs are suggested for enlarging robot workspace in industrial automation. To plan the motion of a multilimbed robot, the arm-leg motion-coordination problem is raised and Task Decomposition is proposed to solve the problem; that is, a given Task described by the destination position and orientation of the end-effector is decomposed into subTasks for arm manipulation and for leg locomotion, respectively. The former is defined as the end-effector position and orientation with respect to the legged main body, and the latter as the main-body position and orientation in the world coordinates. Three approaches are proposed for the Task Decomposition. The approaches are further evaluated in terms of energy consumption, from which an optimal approach can be selected.
-
ICRA - Task Decomposition for multilimbed robots to work in the reachable-but-unorientable space
Proceedings. IEEE International Conference on Robotics and Automation, 1990Co-Authors: Chau Su, Yi Fei ZhengAbstract:Multilimbed industrial robots that have at least one arm and two or more legs are suggested for enlarging robot workspace in industrial automation. To plan the motion of a multilimbed robot, the arm-leg motion-coordination problem is raised and Task Decomposition is proposed to solve the problem; that is, a given Task described by the destination position and orientation of the end-effector is decomposed into subTasks for arm manipulation and for leg locomotion, respectively. The former is defined as the end-effector position and orientation with respect to the legged main body, and the latter as the main-body position and orientation in the world coordinates. Three approaches are proposed for the Task Decomposition. The approaches are further evaluated in terms of energy consumption, from which an optimal approach can be selected. >
-
Task Decomposition for multilimbed robots to work in the reachable-but-unorientable space
Proceedings., IEEE International Conference on Robotics and Automation, 1990Co-Authors: Chau Su, Yi Fei ZhengAbstract:Multilimbed industrial robots that have at least one arm and two or more legs are suggested for enlarging robot workspace in industrial automation. To plan the motion of a multilimbed robot, the arm-leg motion-coordination problem is raised and Task Decomposition is proposed to solve the problem; that is, a given Task described by the destination position and orientation of the end-effector is decomposed into subTasks for arm manipulation and for leg locomotion, respectively. The former is defined as the end-effector position and orientation with respect to the legged main body, and the latter as the main-body position and orientation in the world coordinates. Three approaches are proposed for the Task Decomposition. The approaches are further evaluated in terms of energy consumption, from which an optimal approach can be selected
Peter Stone - One of the best experts on this subject based on the ideXlab platform.
-
Evolving Soccer Keepaway Players Through Task Decomposition
Machine Learning, 2005Co-Authors: Shimon Whiteson, Nate Kohl, Risto Miikkulainen, Peter StoneAbstract:Complex control Tasks can often be solved by decomposing them into hierarchies of manageable subTasks. Such Decompositions require designers to decide how much human knowledge should be used to help learn the resulting components. On one hand, encoding human knowledge requires manual effort and may incorrectly constrain the learner’s hypothesis space or guide it away from the best solutions. On the other hand, it may make learning easier and enable the learner to tackle more complex Tasks. This article examines the impact of this trade-off in Tasks of varying difficulty. A space laid out by two dimensions is explored: (1) how much human assistance is given and (2) how difficult the Task is. In particular, the neuroevolution learning algorithm is enhanced with three different methods for learning the components that result from a Task Decomposition. The first method, coevolution, is mostly unassisted by human knowledge. The second method, layered learning, is highly assisted. The third method, concurrent layered learning, is a novel combination of the first two that attempts to exploit human knowledge while retaining some of coevolution’s flexibility. Detailed empirical results are presented comparing and contrasting these three approaches on two versions of a complex Task, namely robot soccer keepaway, that differ in difficulty of learning. These results confirm that, given a suitable Task Decomposition, neuroevolution can master difficult Tasks. Furthermore, they demonstrate that the appropriate level of human assistance depends critically on the difficulty of the problem.
-
evolving keepaway soccer players through Task Decomposition
Genetic and Evolutionary Computation Conference, 2003Co-Authors: Shimon Whiteson, Nate Kohl, Risto Miikkulainen, Peter StoneAbstract:In some complex control Tasks, learning a direct mapping from an agent's sensors to its actuators is very difficult. For such Tasks, decomposing the problem into more manageable components can make learning feasible. In this paper, we provide a Task Decomposition, in the form of a decision tree, for one such Task. We investigate two different methods of learning the resulting subTasks. The first approach, layered learning, trains each component sequentially in its own training environment, aggressively constraining the search. The second approach, coevolution, learns all the subTasks simultaneously from the same experiences and puts few restrictions on the learning algorithm. We empirically compare these two training methodologies using neuro-evolution, a machine learning algorithm that evolves neural networks. Our experiments, conducted in the domain of simulated robotic soccer keepaway, indicate that neuro-evolution can learn effective behaviors and that the less constrained coevolutionary approach outperforms the sequential approach. These results provide new evidence of coevolution's utility and suggest that solution spaces should not be over-constrained when supplementing the learning of complex Tasks with human knowledge.
-
GECCO - Evolving keepaway soccer players through Task Decomposition
Genetic and Evolutionary Computation — GECCO 2003, 2003Co-Authors: Shimon Whiteson, Nate Kohl, Risto Miikkulainen, Peter StoneAbstract:In some complex control Tasks, learning a direct mapping from an agent's sensors to its actuators is very difficult. For such Tasks, decomposing the problem into more manageable components can make learning feasible. In this paper, we provide a Task Decomposition, in the form of a decision tree, for one such Task. We investigate two different methods of learning the resulting subTasks. The first approach, layered learning, trains each component sequentially in its own training environment, aggressively constraining the search. The second approach, coevolution, learns all the subTasks simultaneously from the same experiences and puts few restrictions on the learning algorithm. We empirically compare these two training methodologies using neuro-evolution, a machine learning algorithm that evolves neural networks. Our experiments, conducted in the domain of simulated robotic soccer keepaway, indicate that neuro-evolution can learn effective behaviors and that the less constrained coevolutionary approach outperforms the sequential approach. These results provide new evidence of coevolution's utility and suggest that solution spaces should not be over-constrained when supplementing the learning of complex Tasks with human knowledge.
Chau Su - One of the best experts on this subject based on the ideXlab platform.
-
Task Decomposition for a multilimbed robot to work in reachable but unorientable space
IEEE Transactions on Robotics and Automation, 1991Co-Authors: Chau Su, Yi Fei ZhengAbstract:Robot manipulators installed on legged mobile platforms are suggested for enlarging robot workspace. To plan the motion of such a system, the arm-platform motion coordination problem is raised, and a Task Decomposition is proposed to solve the problem. A given Task described by the destination position and orientation of the end effector is decomposed into subTasks for arm manipulation and for platform configuration, respectively. The former is defined as the end-effector position and orientation with respect to the platform, and the latter as the platform position and orientation in the base coordinates. Three approaches are proposed for the Task Decomposition. The approaches are also evaluated in terms of the displacements, from which an optimal approach can be selected
-
Task Decomposition for multilimbed robots to work in the reachable-but-unorientable space
Proceedings. IEEE International Conference on Robotics and Automation, 1990Co-Authors: Chau Su, Yi Fei ZhengAbstract:Multilimbed industrial robots that have at least one arm and two or more legs are suggested for enlarging robot workspace in industrial automation. To plan the motion of a multilimbed robot, the arm-leg motion-coordination problem is raised and Task Decomposition is proposed to solve the problem; that is, a given Task described by the destination position and orientation of the end-effector is decomposed into subTasks for arm manipulation and for leg locomotion, respectively. The former is defined as the end-effector position and orientation with respect to the legged main body, and the latter as the main-body position and orientation in the world coordinates. Three approaches are proposed for the Task Decomposition. The approaches are further evaluated in terms of energy consumption, from which an optimal approach can be selected.
-
ICRA - Task Decomposition for multilimbed robots to work in the reachable-but-unorientable space
Proceedings. IEEE International Conference on Robotics and Automation, 1990Co-Authors: Chau Su, Yi Fei ZhengAbstract:Multilimbed industrial robots that have at least one arm and two or more legs are suggested for enlarging robot workspace in industrial automation. To plan the motion of a multilimbed robot, the arm-leg motion-coordination problem is raised and Task Decomposition is proposed to solve the problem; that is, a given Task described by the destination position and orientation of the end-effector is decomposed into subTasks for arm manipulation and for leg locomotion, respectively. The former is defined as the end-effector position and orientation with respect to the legged main body, and the latter as the main-body position and orientation in the world coordinates. Three approaches are proposed for the Task Decomposition. The approaches are further evaluated in terms of energy consumption, from which an optimal approach can be selected. >
-
Task Decomposition for multilimbed robots to work in the reachable-but-unorientable space
Proceedings., IEEE International Conference on Robotics and Automation, 1990Co-Authors: Chau Su, Yi Fei ZhengAbstract:Multilimbed industrial robots that have at least one arm and two or more legs are suggested for enlarging robot workspace in industrial automation. To plan the motion of a multilimbed robot, the arm-leg motion-coordination problem is raised and Task Decomposition is proposed to solve the problem; that is, a given Task described by the destination position and orientation of the end-effector is decomposed into subTasks for arm manipulation and for leg locomotion, respectively. The former is defined as the end-effector position and orientation with respect to the legged main body, and the latter as the main-body position and orientation in the world coordinates. Three approaches are proposed for the Task Decomposition. The approaches are further evaluated in terms of energy consumption, from which an optimal approach can be selected
