Wolpert, D. M. and Kawato, M. (1998). Multiple paired forward and inverse models for motor control. Neural Networks (In press). Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Submitted to Autonomous Agents and Multi Agent Systems 2003 - Automated Derivation Of (Correct)
....architectures. Brand and Hertzmann [2] developed a method for separating human motion data into stylistic and structural components using an extension of Hidden Markov Models. This method assumes the motion is specific to a single class of behavior with stylistic variations. Wolpert and Kawato [18] have proposed an approach for learning multiple paired forward and inverse modules for motor control under various contexts. Our focus in this work is modularization of kinematic motion rather than learning inverse dynamics. Ijspeert et al. 6] have presented an approach for learning nonlinear ....
D. M. Wolpert and M. Kawato. Multiple paired forward and inverse models for motor control. Neural Networks, 11(7-8):1317--1329, 1998.
Models of Generalization in Motor Control - Matsuoka (1998) (Correct)
....of multiple functions within one possible state. This multiple function management mechanism is explored in this section. Narendra and Balakrishnon [1997] have proposed that multiple models can be built depending on the environment, but only one model can be active at any given time. Conversely, Wolpert and Kawato [1998] stated, In (Narendra s) approach . only one controller could be active at any given time as opposed to the blending approach we have chosen and which we believe is a fundamental component of skilled motor control. Their model is based on the responsibility estimator, which determines the ....
Wolpert D. M., and Kawato, M. (1998) Multiple paired forward and inverse models for motor control Neural Networks, submitted.
Human Motor Control: Learning to Control a Time-Varying.. - Karniel, Inbar (2000) (Correct)
....the machine is evolved. This change is the result of many trials of many actions and controllers (by survival of the fittest) and it may last for generations. III. PARAMETERS ESTIMATION In many control schemes and biological modeling, there is a strong need for a model of the system (see [24] [27]) A few examples for such a need were demonstrated in the previous section in the context of adaptive control schemes [8] 10] 21] 22] A parametric model is a model that belongs to a family of models with a finite number of parameters. The modeler s task is first to choose a proper family ....
....more than one possible way (see [5] and [45] In many cases, the parallel architecture implies redundancy, but redundancy can exist without parallelism, as in the inverse kinematics problem. Parallelism also can exist without redundancy, as in some distributed systems (see multiple model control [27], 46] In the following sections, we describe three aspects of these phenomena The first is the issue of multiple feedback loops, which is most common in biological systems and which can jeopardize classical attempts to measure the loop gain. Second, we discuss one possible function of the ....
D. M. Wolpert and M. Kawato, "Multiple paired forward and inverse models for motor control," Neural Networks, vol. 11, pp. 1317--1329, Oct. 1998.
Composition and Decomposition of Internal Models.. - Flanagan, Nakano, .. (Correct)
....the properties of a particular environment or tool, and there would be less relearning involved. Moreover, initial learning of tools and environments may be facilitated by combining stored modules (Ghahramani and Wolpert, 1997) The recently proposed multiple internal model hypothesis (Kawato and Wolpert, 1998; Wolpert and Kawato, 1998; Wolpert et al. 1998) argues for motor control and learning based on such a modular strategy. This model assumes that separate internal models are learned for different environments and also permits mixtures of internal models to cope with a single environment or task. ....
....of a particular environment or tool, and there would be less relearning involved. Moreover, initial learning of tools and environments may be facilitated by combining stored modules (Ghahramani and Wolpert, 1997) The recently proposed multiple internal model hypothesis (Kawato and Wolpert, 1998; Wolpert and Kawato, 1998; Wolpert et al. 1998) argues for motor control and learning based on such a modular strategy. This model assumes that separate internal models are learned for different environments and also permits mixtures of internal models to cope with a single environment or task. Several lines of evidence ....
[Article contains additional citation context not shown here]
Wolpert DM, Kawato M (1998) Multiple paired forward and inverse models for motor control. Neural Networks 11:1317--1329.
Unknown - Self-citation (Wolpert) (Correct)
No context found.
Wolpert, D. M. and Kawato, M. (1998). Multiple paired forward and inverse models for motor control. Neural Networks (In press).
Abnormalities in the Awareness and Control of Action - Frith, Blakemore, Wolpert (2000) Self-citation (Wolpert) (Correct)
....this conguration Recently it has beenproposed that our ability to interact with many dierent objects in a variety of dierent environments relies on a divide and conquer strategy. Complex tasks are decomposed into simpler subtasks, each learned by a separate controller (Ghahramani Wolpert 1997; Wolpert Kawato 1998; Blakemore et al. 1998a) Therefore, rather than having a single controller, multiple controllers develop, each tuned to a particular sensorimotor context. At any given time, one or a subset of these controllers contributes to the nal motor command. The contribution each controller makes to the ....
....full, but is in fact empty, we select the inappropriate controller based on the visual information, but are able to switch controllers when the predicted outcome of our action does not match the actual outcome. This modular learning system, known as the multip le paired predictorcontroller model (Wolpert Kawato 1998), is capable of learning to produce appropriate motor commands under a variety of contexts and can switch rapidly between controllers as the context changes. These features are important for a full model of motor control and motor learning, as the human motor system is capable of very exible, ....
[Article contains additional citation context not shown here]
Wolpert, D. M & Kawato M. 1998 Multiple paired forward and inverse models for motor control. Neural Net. 11, 1317^1329.
Predictive Motor Learning of Temporal Delays - Witney, Goodbody, Wolpert Self-citation (Wolpert) (Correct)
No context found.
WOLPERT,D.M.AND KAWATO, M. Multiple paired forward and inverse models for motor control. Neural Networks 11: 1317--1329, 1998.
MFM: Multiple Forward Model Architecture for Sequence Processing - Raju Bapi Self-citation (Kawato) (Correct)
....Neurobiology Group Kawato Dynamic Brain Project, ERATO, JST 2 2 Hikaridai, Seika, Soraku, Kyoto 619 0288, Japan email: frajubapi, doyag erato.atr.co.jp Abstract A multiple forward model (MFM) architecture is proposed for sequence identification, learning and production. MFM is inspired by Wolpert and Kawato s [ 1998 ] multiple paired forward and inverse models architecture for motor control. In particular, learning of sequencespecific modules and switching among multiple sequences are demonstrated. Appropriate sequence modules are chosen and maintained on the basis of feed forward prediction errors and ....
....India 500 046 In the sequence learning literature, various researchers used neural networks (For example, Bapi and Doya, 1998 ] Dominey, 1995 ] Elman, 1990 ] etc. to learn multiple sequences. Problems with such approaches are long training times and catastrophic forgetting. Recently, Wolpert and Kawato [ 1998 ] proposed multiple paired forward inverse models architecture for human motor learning and successfully applied it to the problem of manipulation of multiple objects [ Haruno et al. 1998 ] They argued that such paired models enable learning and retrieval of the appropriate models based on ....
D. M. Wolpert and M. Kawato. Multiple paired forward and inverse models for motor control. Neural Networks, 11:1317--1329,
Learning Discontinuities with Products-of-Sigmoids for.. - Toussaint, Vijayakumar (2005) (Correct)
No context found.
Wolpert, D., & Kawato, M. (1998). Multiple paired forward and inverse models for motor control. Neural Networks, 11, 1317--1329.
Learning Discontinuities for Switching Between Local Models - Marc Toussaint And (2005) (Correct)
No context found.
D.M. Wolpert and M. Kawato. Multiple paired forward and inverse models for motor control. Neural Networks, 11:1317--1329, 1998.
Adaptive Acquisition of Dynamics Matching in.. - Ogawa, Sakaguchi.. (2006) (Correct)
No context found.
Wolpert DM, Kawato M. Multiple paired forward and inverse models for motor control. Neural Networks 1998;11:1317--1329.
A Bayesian Model of Imitation in Infants and Robots - Rao, Shon, Meltzoff (2004) (1 citation) (Correct)
No context found.
Wolpert, D. M. & Kawato, M. (1998). Multiple paired forward and inverse models for motor control, Neural Networks 11(7-8): 1317-1329.
A Model-Based Goal-Directed Bayesian Framework for.. - Shon, Grimes.. (2004) (Correct)
No context found.
Wolpert, D. and Kawato, M. (1998). Multiple paired forward and inverse models for motor control. Neural Networks, 11:1317--1329.
Mathematical Engineering - Self-Observation Principle For (2003) (Correct)
No context found.
D. M. Wolpert and M. Kawato. Multiple paired forward and inverse models for motor control. Neural Networks, 11:1317-- 1329, 1998. 19
Mathematical Engineering - Self-Observation Principle For (Correct)
No context found.
D. M. Wolpert and M. Kawato. Multiple paired forward and inverse models for motor control. Neural Networks, 11:1317-- 1329, 1998. 19
Learning to Exploit Dynamics for Robot Motor Coordination - Rosenstein (2003) (Correct)
No context found.
D. M. Wolpert and M. Kawato. Multiple paired forward and inverse models for motor control. Neural Networks, 11:1317--1329, 1998.
Interactive Learning in Human-Robot Collaboration - Ogata, Masago, Sugano, Tani (2003) (Correct)
No context found.
D. Wolpert, and M. Kawato, "Multiple paired forward and inverse models for motor control". Neural Networks Vol. 11, pp.1317-1329.
Internal Models in the Cerebellum - Wolpert, al. (1998) (8 citations) (Correct)
No context found.
Wolpert, D.M. and Kawato, M. Multiple paired forward and inverse models for motor control Neural Netw. (in press)
Learning to Perceive the World as Articulated: An Approach for.. - Tani, Nolfi (1998) (13 citations) (Correct)
No context found.
Wolpert, D. & Kawato, M. (1998). Multiple paired forward and inverse models for motor control. Neural Networks 11, 1317--1329.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC