Evolino: Hybrid Neuroevolution/Optimal Linear Search for Sequence Learning

By J. Urgen Schmidhuber, Daan Wierstra, Faustino J. Gomez. 2005

79 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Financial market prediction system with Evolino neural network and Delphi method (2013, background): “Schmidhuber et al. (2005) introduced a general framework of sequence learning algo - rithms, EVOlution of recurrent systems with LINear outputs (Evolino).”
Evolution of autonomous and semi‐autonomous robotic surgical systems: a review of the literature (2011, methodology): “The training algorithm used was the Evolino supervisory evolutionary training framework (39).”
Investigation of financial market prediction by recurrent neural network (2011, methodology): “Investigated network reached good learning and still makes very accurate predictions [1], [10-12].”
Modeling systems with internal state using evolino (2005, methodology): “In this paper, we demonstrate a method called EVOlution of recurrent systems with LINear Outputs (Evolino; [19]), for automatically designing general sequence predictors.”
A System for Robotic Heart Surgery that Learns to Tie Knots Using Recurrent Neural Networks (2006, methodology): “Evolino has been shown to outperform gradient-based methods on continuous trajecto ry generation tasks [10].”
Data-driven forecasting of high-dimensional chaotic systems with long short-term memory networks (2018, methodology): “The LSTM has been successfully applied in sequence modeling [41], speech recognition [39], handwriting recognition [40] and language translation [42].”
Evolutionary Computation for Reinforcement Learning (2012, methodology): “…context, this internal state can record aspects of the agent's observation history , which can help it cope with partial observability (Wieland, 1991; Gomez and Miikkulainen, 1999; Moriarty et al, 1999; Stanley and Miikkulainen, 2002; Igel, 2003; Gomez and Schmidhuber, 2005a,b).”
A Clockwork RNN (2014, background): “This is implemented in a way that can be computed efﬁciently, however, its performance is still inferior to LSTM. Evolino (Schmidhuber et al., 2005; 2007) feeds the input to an RNN (which can be e.g. LSTM to cope with long time lags) and then transforms the RNN outputs to the target sequences via a…”