Gated Fast Weights for On-The-Fly Neural Program Generation
暂无分享,去创建一个
[1] Jürgen Schmidhuber,et al. A ‘Self-Referential’ Weight Matrix , 1993 .
[2] Jürgen Schmidhuber,et al. Highway Networks , 2015, ArXiv.
[3] George Kurian,et al. Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation , 2016, ArXiv.
[4] Jürgen Schmidhuber,et al. Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.
[5] Geoffrey E. Hinton. Using fast weights to deblur old memories , 1987 .
[6] Sepp Hochreiter,et al. Learning to Learn Using Gradient Descent , 2001, ICANN.
[7] Yoshua Bengio,et al. Gated Orthogonal Recurrent Units: On Learning to Forget , 2017, Neural Computation.
[8] Geoffrey E. Hinton,et al. Using Fast Weights to Attend to the Recent Past , 2016, NIPS.
[9] Jason Weston,et al. Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks , 2015, ICLR.
[10] Christoph von der Malsburg,et al. The Correlation Theory of Brain Function , 1994 .
[11] Wojciech Zaremba,et al. Learning to Execute , 2014, ArXiv.
[12] Timothy Dozat,et al. Incorporating Nesterov Momentum into Adam , 2016 .
[13] Alex Graves,et al. Associative Long Short-Term Memory , 2016, ICML.
[14] Hong Yu,et al. Meta Networks , 2017, ICML.
[15] Jürgen Schmidhuber,et al. Evolving Modular Fast-Weight Networks for Control , 2005, ICANN.
[16] Jürgen Schmidhuber,et al. Long Short-Term Memory , 1997, Neural Computation.
[17] J. Schmidhuber,et al. A neural network that embeds its own meta-levels , 1993, IEEE International Conference on Neural Networks.
[18] Geoffrey E. Hinton,et al. Layer Normalization , 2016, ArXiv.
[19] J. Schmidhuber. Reducing the Ratio Between Learning Complexity and Number of Time Varying Variables in Fully Recurrent Nets , 1993 .
[20] Jerome A. Feldman,et al. Dynamic connections in neural networks , 1990, Biological Cybernetics.
[21] Luc Van Gool,et al. Dynamic Filter Networks , 2016, NIPS.
[22] Jürgen Schmidhuber,et al. Deep learning in neural networks: An overview , 2014, Neural Networks.