The Community for Technology Leaders
Neural Networks, IEEE - INNS - ENNS International Joint Conference on (2000)
Como, Italy
July 24, 2000 to July 27, 2000
ISSN: 1098-7576
ISBN: 0-7695-0619-4
pp: 4557
ABSTRACT
Long Short-Term Memory (LSTM) can learn algorithms for temporal pattern processing not learnable by alternative recurrent neural networks (RNNs) or other methods such as Hidden Markov Models (HMMs) and symbolic grammar learning (SGL). Here we present tasks involving arithmetic operations on continual input streams that even LSTM cannot solve. However, an LSTM variant based on “forget gates”, a recent extension, has superior arithmetic capabilities and does solve the tasks.
INDEX TERMS
CITATION

J. Schmidhuber and F. A. Gers, "Neural Processing of Complex Continual Input Streams," Neural Networks, IEEE - INNS - ENNS International Joint Conference on(IJCNN), Como, Italy, 2000, pp. 4557.
doi:10.1109/IJCNN.2000.860830
94 ms
(Ver 3.3 (11022016))