Abstract
Much of the recent interest in artificial neural networks is founded on the development of supervised learning algorithms for nonlinear problems [1, 30, 39, 42, 47]. These algorithms, the most well-known being backpropagation, are able to model a large class of nonlinear transformations by assigning credit to internal “hidden” units. The remaining units—those connected directly to the environment—are generally assumed to be provided with target states. This assumption appears to be a liability; it is by no means clear that such desired outputs can always be provided. Consider, for example, a network serving as a feedforward controller for a robot. Such a network must produce torques as a function of the environmental goal and the current state of the robot. In general, however, the environment provides only the goal and not the torques that achieve the goal. Furthermore, if we assume the existence of an oracle that provides the torques as training data, then there appears to be little reason (other than perhaps speed) not to use the oracle as the controller in place of the network.
This project was supported in part by BRSG 2 S07 RR07047-23 awarded by the Biomedicai Research Support Grant Program, Division of Research Resources, National Institutes of Health and by a grant from Siemens Corporation. The results presented in this paper appeared previously in Jordan (1990).
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Ackley, D. H., Hinton G. E., & Sejnowski T. J. (1985). A learning algorithm for Boltz-mann machines. Cognitive Science, 9, 147–169.
Arbib, M. A. (1981). Perceptual structures and distributed motor control. In V. B. Brooks (Ed.), Handbook of physiology-The nervous system II. Bethesda, MD: American Physiological Society.
Atkeson, C. G. & Reinkensmeyer, D. (1988). Using associative content-addressable memories to control robots. IEEE Conference on Decision and Control. San Francisco, CA.
Barto, A. G. (1989). Connectionist learning for control. Proceedings of the NSF Workshop on Application of Neural Networks to Robotics and Control. Cambridge: MIT Press.
Berkenblit, M. B., Fel’dman, A. G. & Fucson, O. I. (1986). Adaptability of innate motor patterns and motor control. Behavioral and Brain Sciences, 9, 585–638.
Bizzi, E., Accornero, N., Chappie, W., & Hogan, N. (1984). Posture control and trajectory formation during arm movement. Journal of Neuroscience, 4, 2738–2745.
Eccles, J. C. (1977). The Understanding of the Brain. New York: McGraw-Hill.
Fel’dman, A. G. (1980). Superposition of motor programs. I. Rhythmic forearm movements in man. Neuroscience, 5, 544–548.
Fitts, P. M. (1964). Perceptual-motor skill learning. In A. W. Melton (Ed.), Categories of Human Learning. New York: Academic Press.
Flash, T. (1987). The control of hand equilibrium trajectories in multi-joint arm movements. Biological Cybernetics, 57, 257–274.
Flash, T. & Hogan, N. (1985). The coordination of arm movements: An experimentally confirmed mathematical model. The Journal of Neuroscience, 5, 1688–1703.
Greene, P. H. (1982). Why is it easy to control your arms? Journal of Motor Behavior, 9, 2–42.
Gurfinkel, V. S., & Levik, Y. S. (1979). Sensory complexes and sensorimotor integration. Fiziologiya Cheloveka, 5, 399–414.
Hinton, G. E. (1986). A network which learns distributed representations of concepts. Proceedings of the Eighth Annual Conference of the Cognitive Science Society. Hillsdale, NJ: Erlbaum.
Hogan, N. (1984). An organising principle for a class of voluntary movements. Journal of Neuroscience, 4, 2745–2754.
Hogan, N. (1985). Impedance control: An approach to manipulation: Part I-Theory. ASME Journal of Dynamic Systems, Measurement, and Control, 107, 1–24.
Jakobson, R., Fant, G., & Halle, M. (1951). Preliminaries to speech analysis. Cambridge, MA: MIT Press.
Jordan, M. I. (1988). Supervised learning and systems with excess degress of freedom. (COINS Tech. Rep. 88-27). Amherst, MA: University of Massachusetts, Computer and Information Sciences.
Jordan, M. I. (1990). Motor learning and the degrees of freedom problem. In M. Jean-nerod, ed. Attention and Performance, XIII. Hillsdale, NJ: Erlbaum.
Jordan, M. I. (in press). Serial order: A parallel, distributed processing approach. In J. L. Elman and D. E. Rumelhart, (Eds). Advances in Connectionist Theory: Speech. Hillsdale, NJ: Erlbaum.
Jordan, M. I. & Rosenbaum, D. A. (1990). Action. In M. I. Posner (Ed.), Foundations of Cognitive Science. Cambridge, MA: MIT Press.
Jordan, M. I. & Rumelhart, D. E. (1990). Supervised learning with a distal teacher. Submitted to: Cognitive Science.
Kawato, M. (1990). Computational schemes and neural network models for formation and control of multijoint arm trajectory. Proceedings of the NSF Workshop on Application of Neural Networks to Robotics and Control. Cambridge: MIT Press.
Kawato, M., Furukawa, K., & Suzuki, R. (1987). A hierarchical neural-network model for control and learning of voluntary movement. Biological Cybernetics, 57, 169–185.
Kelso, J. A. S. & Holt, K. G. (1980). Exploring a vibratory systems analysis of human movement production. Journal of Neurophysiology, 43, 1183–1196.
Kent, R. D. & Minifie, F. D. (1977). Coarticulation in recent speech production models. Journal of Phonetics, 5, 115–117.
Kiparsky, P. (1975). Comments on the role of phonology in language. In J. F. Kavanagh & J. E. Cutting (Eds.), The Role of Speech in Language. Cambridge: MIT Press.
Koditschek, D. E. (1984). Natural control of robot arms. IEEE Proceedings of the 23rd Conference on Decision and Control, pp. 733–735.
Kuperstein, M. (1987). Adaptive visual-motor coordination in multijoint robots using parallel architecture. IEEE Conference on Robotics and Automation, pp. 1595–1602.
LeCun, Y. 1985. A learning scheme for asymmetric threshold networks. Proceedings of Cognitiva 85. Paris, France.
Lieberman, P. (1975). On the origins of language: An introduction to the evolution of speech. New York: Macmillan.
Lindblom, B. (1983). Economy of speech gestures. In P. F. MacNeilage (Ed.), The Production of Speech. New York: Springer-Verlag.
Lindblom, B., Lubker, J., & Gay, T. (1979). Formant frequencies of some fixed-mandible vowels and a model of speech motor programming by predictive simulation. Journal of Phonetics, 7, 147–161.
Martinet, A. (1968). Phonetics and linguistic evolution. In B. Malmberg, (Ed.), Manual of Phonetics. Amsterdam: North-Holland.
Miller, W. T. (1987). Sensor-based control of robotic manipulators using a general learning algorithm. IEEE Journal of Robotics and Automation, 3:157–165.
Mussa-Ivaldi, F. A., McIntyre, J., & Bizzi, E. (1988). Theoretical and experimental perspectives on arm trajectory formation: A distributed model for motor redundancy. In E. Clementi & S. Chin (Eds.) Biological and Artificial Intelligence Systems. Escom.
Nguyen, D., & Widrow, B. (1988). Personal communication.
Öhman, S. E. G. (1966). Coarticulation in VCV utterances: spectrographic measurements. Journal of the Acoustical Society of America, 39, 151–168.
Parker, D. 1985. Learning-logic. (Tech. Rep. TR-47). Cambridge, MA: MIT Sloan School of Management.
Pineda, F. J. (1987). Generalization of backpropagation to recurrent and higher order neural networks. Proceedings of the IEEE Conference of Neural Information Processing Systems, Palo Alto: Morgan Kaufmann.
Polit, A. & Bizzi, E. (1978). Processes controlling arm movements in monkeys. Science, 201, 1235–1237.
Rumelhart, D. E., Hinton, G. E., Williams, R. J. (1986). Learning internal representations by error propagation. In D. E. Rumelhart & J. L. McClelland (Eds.), Parallel distributed processing: Volume 1. Cambridge, MA: MIT Press.
Salisbury, J. K. (1980). Active stiffness control of a manipulator in Cartesian coordinates. Proceedings of the 19th IEEE Conference on Decision and Control, 95–100.
Saltzman, E. L. & Kelso, J.A. S. (1987). Skilled actions: A task-dynamic approach. Psychological Review, 94, 84–106.
Saltzman, E. L. & Munhall, K. G. (1988). A dynamical approach to gestural patterning in speech production. Submitted to Ecological Psychology.
Uno, Y., Kawato, M., & Suzuki, R. (1987). Formation of optimum trajectory in control of arm movement—minimum torque-change model (Japan IEICE Tech. Rep. MBE 86–79). Osaka, Japan.
Werbos, P. (1974). Beyond regression: New tools for prediction and analysis in the behavioral sciences. Unpublished doctoral dissertation, Harvard University.
Werbos, P. (1987). Building and understanding adaptive systems: A statistical/numerical approach to factory automation and brain research. IEEE Transactions on Systems, Man, and Cybernetics, 11, 7–20.
Widrow, B. & Stearns, S. D. (1985). Adaptive signal processing. Englewood Cliffs, NJ: Prentice-Hall.
Williams, R. J. & Zipser, D. (1988). A learning algorithm for continually running fully recurrent neural networks. (Tech. Rep. ICS 8805). University of California, San Diego, Institute for Cognitive Science.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jordan, M.I. (1993). Constraints on underspecified target trajectories. In: Dario, P., Sandini, G., Aebischer, P. (eds) Robots and Biological Systems: Towards a New Bionics?. NATO ASI Series, vol 102. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-58069-7_23
Download citation
DOI: https://doi.org/10.1007/978-3-642-58069-7_23
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-63461-1
Online ISBN: 978-3-642-58069-7
eBook Packages: Springer Book Archive