Phase-Space Learning for Recurrent Networks
暂无分享,去创建一个
We study the problem of learning nonstatic attractors in recurrent networks. With concepts from dynamical systems theory, we show that this problem can be reduced to three sub-problems, (a) that of embedding the temporal trajectory in phase space, (b) approximating the local vector eld, and (c) function approximation using feedforward networks. This general framework overcomes problems with traditional methods by providing more appropriate error gradients and enforcing stability explicitly. We describe an online version of our method we call ARTISTE, that can learn periodic attractors without teach-forcing.
[1] Garrison W. Cottrell,et al. Some experiments on learning stable network oscillations , 1990, 1990 IJCNN International Joint Conference on Neural Networks.
[2] Garrison W. Cottrell,et al. Learning Mackey-Glass from 25 Examples, Plus or Minus 2 , 1993, NIPS.
[3] Garrison W. Cottrell,et al. Hopf bifurcation and Hopf hopping in recurrent nets , 1993, IEEE International Conference on Neural Networks.
[4] F. Takens. Detecting strange attractors in turbulence , 1981 .