Hierarchical Recurrent Neural Networks for Long-Term Dependencies
作者： Yoshua Bengio , Salah El Hihi
DOI:
关键词:
摘要: … conclusion from the analyses performed on recurrent networks and HMMs to learn to represent … a hierarchical recurrent network with a single-scale fully-connected recurrent network. …
nips.cc
acm.org 参考文章(22)
Satinder P. Singh, Reinforcement learning with a hierarchy of abstract models national conference on artificial intelligence. pp. 202- 207 ,(1992)
Nelly Suaudeau, Un modele probabiliste pour integrer la dimension temporelle dans un systeme de reconnaissance automatique de parole Rennes 1. ,(1994)
Bill G. Horne, C. Lee Giles, Tsungnan Lin, Peter Tiňo, Learning long-term dependencies is not as difficult with NARX recurrent neural networks University of Maryland at College Park. ,(1995)
Richard S. Sutton, TD Models: Modeling the World at a Mixture of Time Scales Machine Learning Proceedings 1995. pp. 531- 539 ,(1995) , 10.1016/B978-1-55860-377-6.50072-4
Y. Bengio, P. Frasconi, Diffusion of context and credit information in Markovian models Journal of Artificial Intelligence Research. ,vol. 3, pp. 249- 270 ,(1995) , 10.1613/JAIR.233
I. Daubechies, The wavelet transform, time-frequency localization and signal analysis IEEE Transactions on Information Theory. ,vol. 36, pp. 961- 1005 ,(1990) , 10.1109/18.57199
F. Brugnara, R. De Mori, D. Giuliani, M. Omologo, A family of parallel hidden Markov models international conference on acoustics, speech, and signal processing. ,vol. 1, pp. 377- 380 ,(1992) , 10.1109/ICASSP.1992.225893
Jürgen Schmidhuber, Learning complex, extended sequences using the principle of history compression Neural Computation. ,vol. 4, pp. 234- 242 ,(1992) , 10.1162/NECO.1992.4.2.234
Kevin J. Lang, Alex H. Waibel, Geoffrey E. Hinton, A time-delay neural network architecture for isolated word recognition Neural Networks. ,vol. 3, pp. 23- 43 ,(1990) , 10.1016/0893-6080(90)90044-L
P. Frasconi, M. Gori, M. Maggini, G. Soda, Unified integration of explicit knowledge and learning by example in recurrent networks IEEE Transactions on Knowledge and Data Engineering. ,vol. 7, pp. 340- 346 ,(1995) , 10.1109/69.382304