BTW, our LSTM Recurrent Networks are in a league by themselves
Learn numerous tasks unlearnable by previous RNNs
Temporal order of distant events in noisy sequences
Info conveyed by event distances
Stable smooth and nonsmooth trajectories, rhythms
Simple regular, context free, context sensitive grammars (Gers, 2000)
Music composition (Eck, 2002)
Reinforcement Learning Robots (Bakker, 2001)
Metalearning (Hochreiter, 2001)
Speech (vs HMMs)? Will try it….
5 LSTM journal publications since 2000
Back to J. Schmidhuber's OOPS page