Schiffmann, W. H. and H. W. Geffers (1993). Adaptive control of dynamic systems by backpropagation networks. Neural Networks. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Integrated Acquisition, Execution, Evaluation, And.. - Kaiser, Giordana, Nuttin (1994) (Correct)
....Robot skill and EO database Preprocessing method database Learning technique database Example database User Interface Robot Sensor Simulation User Tutor Real Robot Figure 4 Components of the interactive programming environment. found and represented operationally (Schiffmann and Geffers, 1993). 4. THE INTERACTIVE PROGRAMMING ENVIRONMENT Apart from the methodological aspects involved in the design of an operational description for an elementary operation, each of the design steps (see figure 2) must also be supported by the programming environment. This programming environment ....
Schiffmann, W. H. and H. W. Geffers (1993). Adaptive control of dynamic systems by backpropagation networks. Neural Networks.
B-Learn II: Case Studies In Robot Learning - Kaiser, Giordana (1994) (Correct)
....system under control, such as qualitative knowledge about the dependency of the change of sensorial input on the change of applied control signal. In order to perform efficient adaptation and enhancement of the controller on line, these characteristics must be found and represented operationally [39, 44]. 1 2 3 60 50 40 30 20 10 10 50 100 150 200 250 300 350 400 450 Forces during insertion operation Fx Fy Fz 1 2 3 4 3 1 2 3 4 Figure 5 Mapping of an example to a sequence of states and induction of structure. 4.2 Learning in navigation In B Learn II the two mobile robots TESEO [34] and ....
W. H. Schiffmann and H. W. Geffers. Adaptive control of dynamicsystems by backpropagation networks. Neural Networks, 6, 1993.
Time-Delay Neural Networks For Control - Kaiser (1994) (Correct)
....the control action y and the corresponding change of state Deltas. In particular, if the sign of the partial derivatives s y is known, the difference between the actual output of the plant and the desired output can be backpropagated through the network in order to adjust the weights (Schiffmann and Geffers, 1993). While (Schiffmann and Geffers, 1993) also report that this adaptation procedure is very sensitive to changes of the learning parameters j or , these problems are less serious when an already operational controller is to be enhanced. e.g. for any j 2 [0:1; 0:9] the adaptation procedure ....
....change of state Deltas. In particular, if the sign of the partial derivatives s y is known, the difference between the actual output of the plant and the desired output can be backpropagated through the network in order to adjust the weights (Schiffmann and Geffers, 1993) While (Schiffmann and Geffers, 1993) also report that this adaptation procedure is very sensitive to changes of the learning parameters j or , these problems are less serious when an already operational controller is to be enhanced. e.g. for any j 2 [0:1; 0:9] the adaptation procedure yielded a controller being able to keep the ....
Schiffmann, W. H. and H. W. Geffers (1993). Adaptive control of dynamic systems by backpropagation networks.
Using Neural Networks For Real-World Adaptive Control - Kaiser, Deck, Retey.. (1995) (Correct)
....the signs of the errors made by the controller, i.e. to know the signs of the system s Jacobian ( y= u) for adaptation. For some tasks with little couplings between the individual inputs and outputs, this qualitative knowledge can be provided a priori, such that model learning is not necessary [14]. The least amount of knowledge that must be available for adaptation is a scalar evaluation (a reward) r of the controller s performance. This evaluation can be used for adaptation in various ways. A first possibility is to extend adaptive model reference control (Fig. 4, 1] To this aim, a ....
W. H. Schiffmann and H. W. Geffers, "Adaptive control of dynamic systems by backpropagation networks", Neural Networks, vol. 6, 1993.
Neural Control Theory: an Overview - Suykens, Bersini (1996) (2 citations) (Correct)
No context found.
Schiffmann W.H., Geffers H.W. (1993). Adaptive control of dynamic systems by back propagation networks, Neural Networks, Vol.6, pp.517-524.
Distal Learning for Inverse Modelling of Dynamical Systems - Toudeft, Gallinari (Correct)
No context found.
"Adaptive Control of Dynamic Systems by Back Propagation Networks", Neural Networks, Vol. 6, pp. 517-524.
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