Title :
Neural processing of complex continual input streams
Author :
Gers, Felix A. ; Schmidhuber, Jurgen
Author_Institution :
IDSIA, Lugano, Switzerland
Abstract :
Long short-term memory (LSTM) can learn algorithms for temporal pattern processing not learnable by alternative recurrent neural networks or other methods such as hidden Markov models and symbolic grammar learning. Here, we present tasks involving arithmetic operations on continual input streams that even LSTM cannot solve. However, an LSTM variant based on “forget gates,” has superior arithmetic capabilities and does solve the tasks
Keywords :
content-addressable storage; learning (artificial intelligence); recurrent neural nets; complex continual input streams; forget gates; learning; long short-term memory; recurrent neural networks; Arithmetic; Error correction; Genetic programming; Hidden Markov models; Learning systems; Protection; Recurrent neural networks; State-space methods;
Conference_Titel :
Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Conference_Location :
Como
Print_ISBN :
0-7695-0619-4
DOI :
10.1109/IJCNN.2000.860830
