Initialization matters: Orthogonal Predictive State Recurrent Neural Networks
暂无分享,去创建一个
Byron Boots | Krzysztof Choromanski | Carlton Downey | Byron Boots | K. Choromanski | Carlton Downey
[1] Krzysztof Choromanski,et al. The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings , 2017, NIPS.
[2] Geoffrey J. Gordon,et al. Supervised Learning for Dynamical System Learning , 2015, NIPS.
[3] Sanjiv Kumar,et al. Binary embeddings with structured hashed projections , 2015, ICML.
[4] Sanjiv Kumar,et al. Orthogonal Random Features , 2016, NIPS.
[5] Richard S. Sutton,et al. Predictive Representations of State , 2001, NIPS.
[6] Krzysztof Choromanski,et al. Recycling Randomness with Structure for Sublinear time Kernel Expansions , 2016, ICML.
[7] Benjamin Recht,et al. Random Features for Large-Scale Kernel Machines , 2007, NIPS.
[8] Surya Ganguli,et al. Exact solutions to the nonlinear dynamics of learning in deep linear neural networks , 2013, ICLR.
[9] Georg Heigold,et al. End-to-end text-dependent speaker verification , 2015, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
[10] Lukás Burget,et al. Recurrent neural network based language model , 2010, INTERSPEECH.
[11] Yoshua Bengio,et al. Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.
[12] Surya Ganguli,et al. Memory traces in dynamical systems , 2008, Proceedings of the National Academy of Sciences.
[13] Francis R. Bach,et al. Sharp analysis of low-rank kernel matrix approximations , 2012, COLT.
[14] Stefano Soatto,et al. Emergence of invariance and disentangling in deep representations , 2017 .
[15] Hui Zhang,et al. New bounds for circulant Johnson-Lindenstrauss embeddings , 2013, ArXiv.
[16] Haim Sompolinsky,et al. Short-term memory in orthogonal neural networks. , 2004, Physical review letters.
[17] Aicke Hinrichs,et al. Johnson‐Lindenstrauss lemma for circulant matrices* * , 2010, Random Struct. Algorithms.
[18] Bernard Chazelle,et al. Approximate nearest neighbors and the fast Johnson-Lindenstrauss transform , 2006, STOC '06.
[19] Yoshua Bengio,et al. Unitary Evolution Recurrent Neural Networks , 2015, ICML.
[20] I. J. Schoenberg. Metric spaces and completely monotone functions , 1938 .
[21] Byron Boots,et al. Hilbert Space Embeddings of Predictive State Representations , 2013, UAI.
[22] Anne Morvan,et al. Structured adaptive and random spinners for fast machine learning computations , 2016, AISTATS.
[23] Yann LeCun,et al. Recurrent Orthogonal Networks and Long-Memory Tasks , 2016, ICML.
[24] Byron Boots,et al. Predictive State Recurrent Neural Networks , 2017, NIPS.
[25] Jürgen Schmidhuber,et al. Long Short-Term Memory , 1997, Neural Computation.
[26] Jan Vyb'iral. A variant of the Johnson-Lindenstrauss lemma for circulant matrices , 2010, 1002.2847.
[27] Yoshua Bengio,et al. On the Properties of Neural Machine Translation: Encoder–Decoder Approaches , 2014, SSST@EMNLP.
[28] Ameya Velingker,et al. Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees , 2018, ICML.
[29] Le Song,et al. A Hilbert Space Embedding for Distributions , 2007, Discovery Science.
[30] Yoshua Bengio,et al. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention , 2015, ICML.