The Experts below are selected from a list of 29430 Experts worldwide ranked by ideXlab platform

Yoji Uno - One of the best experts on this subject based on the ideXlab platform.

  • learning of real robot s inverse dynamics by a Forward Propagation learning rule
    Electrical Engineering in Japan, 2007
    Co-Authors: Hiroki Mori, Yoshihiro Ohama, Naohiro Fukumura, Yoji Uno
    Abstract:

    A Forward-Propagation learning rule (FPL) has been proposed for a neural network (NN) to learn an inverse model of a controlled object. A feature of FPL is that the trajectory error propagates Forward in NN and appropriate values of two learning parameters are required to be set. FPL has only been simulated to several kinds of controlled objects such as a two-link arm in a horizontal plane. In this work, we applied FPL to AIBO and showed the validity of FPL on a real controlled object. At first, we tested a learning experiment of an inverse dynamic of a two-link arm in a sagittal plane with viscosity and Coulomb friction by computer simulation. In this simulation, a low-pass filter (LPF) was applied to realized trajectories because coulomb friction vibrates them. From the simulation results, we found that the learning process is stable by some adequate sets of the learning parameters although it is more sensitive to the values of the parameters owing to friction and gravity terms. Finally, we tested applying FPL to motor control of AIBO's leg. The inverse dynamics model was acquired by FPL with only about 150 learning iterations. From these results, the validity of the FPL was confirmed by the real robot control experiments. © 2007 Wiley Periodicals, Inc. Electr Eng Jpn, 161(4): 38–48, 2007; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/eej.20456

  • a Forward Propagation learning rule for neural inverse models in consideration of the correlation of propagated errors
    Systems and Computers in Japan, 2006
    Co-Authors: Yoshihiro Ohama, Naohiro Fukumura, Yoji Uno
    Abstract:

    We have proposed the Forward-Propagation rule (FP) as an inverse model learning scheme from the viewpoint of biological motor control. This learning scheme is based on a Newton-like method, by which multilayered neural network can acquire an inverse model of the controlled object by a small number of iterative learning trials. There is a problem, however, that the learning procedure, which is characterized by estimation of the supervisor's signal for the input–output signal of the neuron, and also the solution of a linear multiple regression problem for updating the connection weights, is complicated, making it difficult to analyze the learning process. This paper introduces the correlation of the propagated error signal from the viewpoint of the maximum-likelihood method in order to realize a goal-directed learning, which has not hitherto been considered in FP, and extends the learning rule to the generalized least-square method. As a result, it is clearly shown that the learning rule in FP is an approximate gradient method. The learning ability of the method is demonstrated by computer simulation. The proposed procedure contains a regularization term derived from the logarithmic likelihood, and the behavior after the convergence of learning exhibits a more stable tendency than in the conventional method. It is also shown that learning can be performed by a simplified method in which the error is simply propagated in the Forward direction. © 2006 Wiley Periodicals, Inc. Syst Comp Jpn, 37(13): 54–66, 2006; Published online in Wiley InterScience (). DOI 10.1002sscj.20484

  • a simplified Forward Propagation learning rule applied to adaptive closed loop control
    International Conference on Artificial Neural Networks, 2005
    Co-Authors: Yoshihiro Ohama, Naohiro Fukumura, Yoji Uno
    Abstract:

    In terms of computational neuroscience, several theoretical learning schemes have been proposed to acquire suitable motor controllers in the human brain. The controllers have been classified into a feedForward manner and a feedback manner as inverse models of controlled objects. For learning a feedForward controller, we have proposed a Forward-Propagation learning (FPL) rule which propagates error "Forward" in a multi-layered neural network to solve a credit assignment problem. In the current work, FPL is simplified to realize accurate learning, and to be extended to adaptive feedback control. The suitability of a proposed scheme is confirmed by computer simulation.

  • a Forward Propagation learning rule for neural inverse models using a method of recursive least squares
    Systems and Computers in Japan, 2005
    Co-Authors: Yoshihiro Ohama, Naohiro Fukumura, Yoji Uno
    Abstract:

    A Forward-Propagation learning scheme has been proposed to acquire inverse models of controlled objects in multilayered neural networks. This scheme is quite different from back-Propagation learning rule. The algorithm of the Forward-Propagation rule consists of two stages. One is the estimation of the instruction signal at each layer by the Newton-like method, and the other is the updating of the connection weights by linear multiple regression. In this scheme, convergence of learning has been faster than other schemes based on backPropagation rule. However, the problems arise that complex parameters must be set for learning and the learning process is too complex and sometimes stops. This paper proposes to use a method of recursive least squares in the Forward-Propagation rule. The effectiveness of the proposed method is confirmed by computer simulation for the learning of the inverse dynamics model for a two-link arm. © 2005 Wiley Periodicals, Inc. Syst Comp Jpn, 36(8): 71–80, 2005; Published online in Wiley InterScience (). DOI 10.1002sscj.20237

  • a Forward Propagation learning rule for acquiring inverse models in multilayered neural networks
    Electronics and Communications in Japan Part Ii-electronics, 2005
    Co-Authors: Kazuyuki Nagasawa, Naohiro Fukumura, Yoji Uno
    Abstract:

    Many proposals have been presented for the acquisition of inverse models in multilayered neural networks. However, most are concerned with the backPropagation rule or its improvement. In learning in a multilayered neural network based on the backPropagation rule, there must be a supervisor signal for the output layer, and there must be a particular path to propagate the learning signal in the reverse direction. In addition, convergence is slow due to the use of the method of steepest descent in updating the weights. Consequently, this paper proposes a Forward-Propagation rule in which the neural network model is trained by propagating the motion error exhibited by the control object in the Forward direction in the neural network. In the proposed algorithm, the extended Newton's method is used to derive the goal signal (which corresponds to the supervisor signal) in the hidden layer and the output layer. Since linear multiple regression can be used in weight updating for realizing the goal signals, the iteration of weight updating can be reduced compared to the method of steepest descent. A computer simulation was performed for acquisition of a two-link arm model, and the effectiveness of the proposed learning scheme was verified. © 2005 Wiley Periodicals, Inc. Electron Comm Jpn Pt 2, 88(2): 59–68, 2005; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecjb.20148

Omar M Knio - One of the best experts on this subject based on the ideXlab platform.

  • uncertainty quantification in md simulations of concentration driven ionic flow through a silica nanopore i sensitivity to physical parameters of the pore
    Journal of Chemical Physics, 2013
    Co-Authors: Francesco Rizzi, Reese E Jones, Bert Debusschere, Omar M Knio
    Abstract:

    In this article, uncertainty quantification is applied to molecular dynamics (MD) simulations of concentration driven ionic flow through a silica nanopore. We consider a silica pore model connecting two reservoirs containing a solution of sodium (Na+) and chloride (Cl−) ions in water. An ad hoc concentration control algorithm is developed to simulate a concentration driven counter flow of ions through the pore, with the ionic flux being the main observable extracted from the MD system. We explore the sensitivity of the system to two physical parameters of the pore, namely, the pore diameter and the gating charge. First we conduct a quantitative analysis of the impact of the pore diameter on the ionic flux, and interpret the results in terms of the interplay between size effects and ion mobility. Second, we analyze the effect of gating charge by treating the charge density over the pore surface as an uncertain parameter in a Forward Propagation study. Polynomial chaos expansions and Bayesian inference are ...

  • uncertainty quantification in md simulations of concentration driven ionic flow through a silica nanopore ii uncertain potential parameters
    Journal of Chemical Physics, 2013
    Co-Authors: Francesco Rizzi, Reese E Jones, Bert Debusschere, Omar M Knio
    Abstract:

    This article extends the uncertainty quantification analysis introduced in Paper I for molecular dynamics (MD) simulations of concentration driven ionic flow through a silica nanopore. Attention is now focused on characterizing, for a fixed pore diameter of D = 21 A, the sensitivity of the system to the Lennard-Jones energy parameters, ɛNa+ and ɛCl−, defining the depth of the potential well for the two ions Na+ and Cl−, respectively. A Forward Propagation analysis is applied to map the uncertainty in these parameters to the MD predictions of the ionic fluxes. Polynomial chaos expansions and Bayesian inference are exploited to isolate the effect of the intrinsic noise, stemming from thermal fluctuations of the atoms, and properly quantify the impact of parametric uncertainty on the target MD predictions. A Bayes factor analysis is then used to determine the most suitable regression model to represent the MD noisy data. The study shows that the response surface of the Na+ conductance can be effectively infe...

Yoshihiro Ohama - One of the best experts on this subject based on the ideXlab platform.

  • learning of real robot s inverse dynamics by a Forward Propagation learning rule
    Electrical Engineering in Japan, 2007
    Co-Authors: Hiroki Mori, Yoshihiro Ohama, Naohiro Fukumura, Yoji Uno
    Abstract:

    A Forward-Propagation learning rule (FPL) has been proposed for a neural network (NN) to learn an inverse model of a controlled object. A feature of FPL is that the trajectory error propagates Forward in NN and appropriate values of two learning parameters are required to be set. FPL has only been simulated to several kinds of controlled objects such as a two-link arm in a horizontal plane. In this work, we applied FPL to AIBO and showed the validity of FPL on a real controlled object. At first, we tested a learning experiment of an inverse dynamic of a two-link arm in a sagittal plane with viscosity and Coulomb friction by computer simulation. In this simulation, a low-pass filter (LPF) was applied to realized trajectories because coulomb friction vibrates them. From the simulation results, we found that the learning process is stable by some adequate sets of the learning parameters although it is more sensitive to the values of the parameters owing to friction and gravity terms. Finally, we tested applying FPL to motor control of AIBO's leg. The inverse dynamics model was acquired by FPL with only about 150 learning iterations. From these results, the validity of the FPL was confirmed by the real robot control experiments. © 2007 Wiley Periodicals, Inc. Electr Eng Jpn, 161(4): 38–48, 2007; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/eej.20456

  • a Forward Propagation learning rule for neural inverse models in consideration of the correlation of propagated errors
    Systems and Computers in Japan, 2006
    Co-Authors: Yoshihiro Ohama, Naohiro Fukumura, Yoji Uno
    Abstract:

    We have proposed the Forward-Propagation rule (FP) as an inverse model learning scheme from the viewpoint of biological motor control. This learning scheme is based on a Newton-like method, by which multilayered neural network can acquire an inverse model of the controlled object by a small number of iterative learning trials. There is a problem, however, that the learning procedure, which is characterized by estimation of the supervisor's signal for the input–output signal of the neuron, and also the solution of a linear multiple regression problem for updating the connection weights, is complicated, making it difficult to analyze the learning process. This paper introduces the correlation of the propagated error signal from the viewpoint of the maximum-likelihood method in order to realize a goal-directed learning, which has not hitherto been considered in FP, and extends the learning rule to the generalized least-square method. As a result, it is clearly shown that the learning rule in FP is an approximate gradient method. The learning ability of the method is demonstrated by computer simulation. The proposed procedure contains a regularization term derived from the logarithmic likelihood, and the behavior after the convergence of learning exhibits a more stable tendency than in the conventional method. It is also shown that learning can be performed by a simplified method in which the error is simply propagated in the Forward direction. © 2006 Wiley Periodicals, Inc. Syst Comp Jpn, 37(13): 54–66, 2006; Published online in Wiley InterScience (). DOI 10.1002sscj.20484

  • a simplified Forward Propagation learning rule applied to adaptive closed loop control
    International Conference on Artificial Neural Networks, 2005
    Co-Authors: Yoshihiro Ohama, Naohiro Fukumura, Yoji Uno
    Abstract:

    In terms of computational neuroscience, several theoretical learning schemes have been proposed to acquire suitable motor controllers in the human brain. The controllers have been classified into a feedForward manner and a feedback manner as inverse models of controlled objects. For learning a feedForward controller, we have proposed a Forward-Propagation learning (FPL) rule which propagates error "Forward" in a multi-layered neural network to solve a credit assignment problem. In the current work, FPL is simplified to realize accurate learning, and to be extended to adaptive feedback control. The suitability of a proposed scheme is confirmed by computer simulation.

  • a Forward Propagation learning rule for neural inverse models using a method of recursive least squares
    Systems and Computers in Japan, 2005
    Co-Authors: Yoshihiro Ohama, Naohiro Fukumura, Yoji Uno
    Abstract:

    A Forward-Propagation learning scheme has been proposed to acquire inverse models of controlled objects in multilayered neural networks. This scheme is quite different from back-Propagation learning rule. The algorithm of the Forward-Propagation rule consists of two stages. One is the estimation of the instruction signal at each layer by the Newton-like method, and the other is the updating of the connection weights by linear multiple regression. In this scheme, convergence of learning has been faster than other schemes based on backPropagation rule. However, the problems arise that complex parameters must be set for learning and the learning process is too complex and sometimes stops. This paper proposes to use a method of recursive least squares in the Forward-Propagation rule. The effectiveness of the proposed method is confirmed by computer simulation for the learning of the inverse dynamics model for a two-link arm. © 2005 Wiley Periodicals, Inc. Syst Comp Jpn, 36(8): 71–80, 2005; Published online in Wiley InterScience (). DOI 10.1002sscj.20237

  • learning of real robot s inverse dynamics by a Forward Propagation learning rule
    Ieej Transactions on Electronics Information and Systems, 2005
    Co-Authors: Hiroki Mori, Yoshihiro Ohama, Naohiro Fukumura, Yoji Uno
    Abstract:

    A Forward-Propagation learning rule (FPL) has been proposed for Neural Network (NN) to learn an inverse model of a controlled object. A feature of FPL is that the trajectory error propagates Forward in NN and appropriate values of two learning parameters are required to be set. FPL has been only simulated to several kinds of controlled objects such as a 2-link arm in a horizontal plane. In this work, we applied FPL to AIBO so that we showed validity of FPL on a real controlled object. At first, we tested a learning experiment of an inverse dynamics of a 2-link arm in a sagittal plane with viscosity and coulomb friction by computer simulation. In this simulation, low pass filter (LPF) was applied to realized trajectories because coulomb friction vibrates them. From results of simulation, we found that the learning process is stable by some adequate sets of the learning parameters although it is more sensitive to the values of the parameters owing to friction and gravity terms. Finally, we tested applying FPL to motor control of AIBO's leg. The inverse dynamics model was acquired by FPL with only about 150 learning iterations. From these results, the validity of the FPL was confirmed by the real robot control experiments.

Francesco Rizzi - One of the best experts on this subject based on the ideXlab platform.

  • uncertainty quantification in md simulations of concentration driven ionic flow through a silica nanopore i sensitivity to physical parameters of the pore
    Journal of Chemical Physics, 2013
    Co-Authors: Francesco Rizzi, Reese E Jones, Bert Debusschere, Omar M Knio
    Abstract:

    In this article, uncertainty quantification is applied to molecular dynamics (MD) simulations of concentration driven ionic flow through a silica nanopore. We consider a silica pore model connecting two reservoirs containing a solution of sodium (Na+) and chloride (Cl−) ions in water. An ad hoc concentration control algorithm is developed to simulate a concentration driven counter flow of ions through the pore, with the ionic flux being the main observable extracted from the MD system. We explore the sensitivity of the system to two physical parameters of the pore, namely, the pore diameter and the gating charge. First we conduct a quantitative analysis of the impact of the pore diameter on the ionic flux, and interpret the results in terms of the interplay between size effects and ion mobility. Second, we analyze the effect of gating charge by treating the charge density over the pore surface as an uncertain parameter in a Forward Propagation study. Polynomial chaos expansions and Bayesian inference are ...

  • uncertainty quantification in md simulations of concentration driven ionic flow through a silica nanopore ii uncertain potential parameters
    Journal of Chemical Physics, 2013
    Co-Authors: Francesco Rizzi, Reese E Jones, Bert Debusschere, Omar M Knio
    Abstract:

    This article extends the uncertainty quantification analysis introduced in Paper I for molecular dynamics (MD) simulations of concentration driven ionic flow through a silica nanopore. Attention is now focused on characterizing, for a fixed pore diameter of D = 21 A, the sensitivity of the system to the Lennard-Jones energy parameters, ɛNa+ and ɛCl−, defining the depth of the potential well for the two ions Na+ and Cl−, respectively. A Forward Propagation analysis is applied to map the uncertainty in these parameters to the MD predictions of the ionic fluxes. Polynomial chaos expansions and Bayesian inference are exploited to isolate the effect of the intrinsic noise, stemming from thermal fluctuations of the atoms, and properly quantify the impact of parametric uncertainty on the target MD predictions. A Bayes factor analysis is then used to determine the most suitable regression model to represent the MD noisy data. The study shows that the response surface of the Na+ conductance can be effectively infe...

Naohiro Fukumura - One of the best experts on this subject based on the ideXlab platform.

  • learning of real robot s inverse dynamics by a Forward Propagation learning rule
    Electrical Engineering in Japan, 2007
    Co-Authors: Hiroki Mori, Yoshihiro Ohama, Naohiro Fukumura, Yoji Uno
    Abstract:

    A Forward-Propagation learning rule (FPL) has been proposed for a neural network (NN) to learn an inverse model of a controlled object. A feature of FPL is that the trajectory error propagates Forward in NN and appropriate values of two learning parameters are required to be set. FPL has only been simulated to several kinds of controlled objects such as a two-link arm in a horizontal plane. In this work, we applied FPL to AIBO and showed the validity of FPL on a real controlled object. At first, we tested a learning experiment of an inverse dynamic of a two-link arm in a sagittal plane with viscosity and Coulomb friction by computer simulation. In this simulation, a low-pass filter (LPF) was applied to realized trajectories because coulomb friction vibrates them. From the simulation results, we found that the learning process is stable by some adequate sets of the learning parameters although it is more sensitive to the values of the parameters owing to friction and gravity terms. Finally, we tested applying FPL to motor control of AIBO's leg. The inverse dynamics model was acquired by FPL with only about 150 learning iterations. From these results, the validity of the FPL was confirmed by the real robot control experiments. © 2007 Wiley Periodicals, Inc. Electr Eng Jpn, 161(4): 38–48, 2007; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/eej.20456

  • a Forward Propagation learning rule for neural inverse models in consideration of the correlation of propagated errors
    Systems and Computers in Japan, 2006
    Co-Authors: Yoshihiro Ohama, Naohiro Fukumura, Yoji Uno
    Abstract:

    We have proposed the Forward-Propagation rule (FP) as an inverse model learning scheme from the viewpoint of biological motor control. This learning scheme is based on a Newton-like method, by which multilayered neural network can acquire an inverse model of the controlled object by a small number of iterative learning trials. There is a problem, however, that the learning procedure, which is characterized by estimation of the supervisor's signal for the input–output signal of the neuron, and also the solution of a linear multiple regression problem for updating the connection weights, is complicated, making it difficult to analyze the learning process. This paper introduces the correlation of the propagated error signal from the viewpoint of the maximum-likelihood method in order to realize a goal-directed learning, which has not hitherto been considered in FP, and extends the learning rule to the generalized least-square method. As a result, it is clearly shown that the learning rule in FP is an approximate gradient method. The learning ability of the method is demonstrated by computer simulation. The proposed procedure contains a regularization term derived from the logarithmic likelihood, and the behavior after the convergence of learning exhibits a more stable tendency than in the conventional method. It is also shown that learning can be performed by a simplified method in which the error is simply propagated in the Forward direction. © 2006 Wiley Periodicals, Inc. Syst Comp Jpn, 37(13): 54–66, 2006; Published online in Wiley InterScience (). DOI 10.1002sscj.20484

  • a simplified Forward Propagation learning rule applied to adaptive closed loop control
    International Conference on Artificial Neural Networks, 2005
    Co-Authors: Yoshihiro Ohama, Naohiro Fukumura, Yoji Uno
    Abstract:

    In terms of computational neuroscience, several theoretical learning schemes have been proposed to acquire suitable motor controllers in the human brain. The controllers have been classified into a feedForward manner and a feedback manner as inverse models of controlled objects. For learning a feedForward controller, we have proposed a Forward-Propagation learning (FPL) rule which propagates error "Forward" in a multi-layered neural network to solve a credit assignment problem. In the current work, FPL is simplified to realize accurate learning, and to be extended to adaptive feedback control. The suitability of a proposed scheme is confirmed by computer simulation.

  • a Forward Propagation learning rule for neural inverse models using a method of recursive least squares
    Systems and Computers in Japan, 2005
    Co-Authors: Yoshihiro Ohama, Naohiro Fukumura, Yoji Uno
    Abstract:

    A Forward-Propagation learning scheme has been proposed to acquire inverse models of controlled objects in multilayered neural networks. This scheme is quite different from back-Propagation learning rule. The algorithm of the Forward-Propagation rule consists of two stages. One is the estimation of the instruction signal at each layer by the Newton-like method, and the other is the updating of the connection weights by linear multiple regression. In this scheme, convergence of learning has been faster than other schemes based on backPropagation rule. However, the problems arise that complex parameters must be set for learning and the learning process is too complex and sometimes stops. This paper proposes to use a method of recursive least squares in the Forward-Propagation rule. The effectiveness of the proposed method is confirmed by computer simulation for the learning of the inverse dynamics model for a two-link arm. © 2005 Wiley Periodicals, Inc. Syst Comp Jpn, 36(8): 71–80, 2005; Published online in Wiley InterScience (). DOI 10.1002sscj.20237

  • a Forward Propagation learning rule for acquiring inverse models in multilayered neural networks
    Electronics and Communications in Japan Part Ii-electronics, 2005
    Co-Authors: Kazuyuki Nagasawa, Naohiro Fukumura, Yoji Uno
    Abstract:

    Many proposals have been presented for the acquisition of inverse models in multilayered neural networks. However, most are concerned with the backPropagation rule or its improvement. In learning in a multilayered neural network based on the backPropagation rule, there must be a supervisor signal for the output layer, and there must be a particular path to propagate the learning signal in the reverse direction. In addition, convergence is slow due to the use of the method of steepest descent in updating the weights. Consequently, this paper proposes a Forward-Propagation rule in which the neural network model is trained by propagating the motion error exhibited by the control object in the Forward direction in the neural network. In the proposed algorithm, the extended Newton's method is used to derive the goal signal (which corresponds to the supervisor signal) in the hidden layer and the output layer. Since linear multiple regression can be used in weight updating for realizing the goal signals, the iteration of weight updating can be reduced compared to the method of steepest descent. A computer simulation was performed for acquisition of a two-link arm model, and the effectiveness of the proposed learning scheme was verified. © 2005 Wiley Periodicals, Inc. Electron Comm Jpn Pt 2, 88(2): 59–68, 2005; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecjb.20148