“Learning fast neural network emulators for physics-based models” by Grzeszczuk, Terzopoulos and Hinton
Conference:
Type(s):
Interest Area:
- Production & Animation and Technical
Title:
- Learning fast neural network emulators for physics-based models
Session/Category Title: Animation
Presenter(s)/Author(s):
Abstract:
Generation of physically realistic animation using trained neural networks that can emulate non-trivial physics-based models one or two orders of magnitude faster than conventional numerical simulation.
References:
1 “Learning Internal Representations by Error Backpropagation”, Rumelhart, D. E. and Hinton, G. E. and Williams, R.J., in “Parallel Distributed Processing: Explorations in the Microstructure of Cognition”, MIT Press, 1986, ed. Rumelhart, D. E. and McCleland, J. L. and the PDP Research Group, vol. 1, 318-362.
2 “Automated Learning of Muscle-Actuated Locomotion through control abstraction”, R. Grzeszczuk, D. Terzopoulos, Proc. ACM SIGGRAPH 95 Conference, Los Angeles, CA, August, 1995, in Computer Graphics Proceedings, Annual Conference Series, 1995, 63-70.
3 “Animating Human Athletics”, Jessica K. Hodgins and Wayne L. Wooten and David C. Brogan and James F. O’Brien, Proc. ACM SIGGRAPH 95 Conference, Los Angeles, CA, August, 1995, in Computer Graphics Proceedings, Annual Conference Series, 1995, 71-78.
