| Title | State prediction: a constructive method to program recurrent neural networks |
| Publication Type | Conference Paper |
| Year of Publication | 2011 |
| Authors | Reinhart F, Steil JJ |
| Conference Name | Artificial Neural Networks and Machine Learning – ICANN 2011 : 21st International Conference on Artificial Neural Networks, Espoo, Finland, June 14-17, 2011, Proceedings, Part I |
| Pagination | 159–166 |
| Publisher | Springer |
| Abstract | We introduce a novel technique to program desired state sequences into recurrent neural networks in one shot. The basic methodology and its scalability to large and input-driven networks is demonstrated by shaping attractor landscapes, transient dynamics and programming limit cycles. The approach unifies programming of transient and attractor dynamics in a generic framework. |
| DOI | 10.1007/978-3-642-21735-7_20 |
