Attempting to reduce the vanishing gradient effect through a novel recurrent multiscale architecture
暂无分享,去创建一个
[1] Jürgen Schmidhuber,et al. Long Short-Term Memory , 1997, Neural Computation.
[2] Ronald J. Williams,et al. Gradient-based learning algorithms for recurrent networks and their computational complexity , 1995 .
[3] S. C. Kremer,et al. Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies , 2001 .
[4] Yoshua Bengio,et al. Hierarchical Recurrent Neural Networks for Long-Term Dependencies , 1995, NIPS.
[5] John F. Kolen,et al. Insertion of Prior Knowledge , 2001 .
[6] A.H. Tewfik,et al. Correlation structure of the discrete wavelet coefficients of fractional Brownian motion , 1992, IEEE Trans. Inf. Theory.
[7] S.M. Kogon,et al. Efficient generation of long-memory signals using lattice structures , 1995, Conference Record of The Twenty-Ninth Asilomar Conference on Signals, Systems and Computers.
[8] Kwok Yip Szeto,et al. Rules extraction in short memory time series using genetic algorithms , 2001 .
[9] Yoshua Bengio,et al. Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies , 2001 .
[10] Peter Tiño,et al. Learning long-term dependencies in NARX recurrent neural networks , 1996, IEEE Trans. Neural Networks.
[11] Yoshua Bengio,et al. Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.
[12] Amir B. Geva,et al. ScaleNet-multiscale neural-network architecture for time series prediction , 1998, IEEE Trans. Neural Networks.
[13] Dominik R. Dersch,et al. Multiresolution Forecasting for Futures Trading , 2001 .