Current Neural Network learning algorithms are limited in their ability to model non-linear dynamical systems. Most supervised gradient-based recurrent neural networks (RNNs) suffer from a vanishing error signal that prevents learning from inputs far in the past. Those that do not, still have problems when there are numerous local minima. We introduce a general framework for sequence learning, EVOlution of recurrent systems with LINear outputs (Evolino). Evolino uses evolution to discover good RNN hidden node weights, while using methods such as linear regression or quadratic programming to compute optimal linear mappings from hidden state to output. Using the Long Short-Term Memory RNN Architecture, the method is tested in three very different problem domains: 1) context-sensitive languages, 2) multiple superimposed sine waves, and 3) the Mackey-Glass system. Evolino performs exceptionally well across all tasks, where other methods show notable deficiencies in some.
|Original language||English (US)|
|Title of host publication||IJCAI International Joint Conference on Artificial Intelligence|
|Number of pages||6|
|State||Published - Dec 1 2005|