Training recurrent networks

By M. Pedersen. 1997

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Yoshua Bengio
2. J. Urgen Schmidhuber
3. Ronald J. Williams
4. David Zipser
5. Sergey Levine
6. Lars Kai Hansen
7. Quoc V. Le
8. Ruslan Salakhutdinov

Citations in the corpus

• Adaptive Regularization in Neural Network Modeling (1996, methodology): “Gauss-Newton approximation. Many studies have reported signicant training speedup by using second order methods, see e.g., [22], [ 35 ].”
• Gradient-based learning algorithms for recurrent networks and their computational complexity (1995, background): “…studying supervised learning tasks for recurrent nets (Doya & Yoshizawa, 1989; Jordan, 1986; Narendra & Parthasarathy, 1990; Pineda, 1988; Rohwer & Renals, 1989; Williams & Zipser, 1989a; 1989b) is to replace, during training, the actual output y;,(¢) of a unit by the teacher signal…”