MC-LSTM: Mass-conserving LSTM
作者： Pieter-Jan Hoedt , Frederik Kratzert , Daniel Klotz , Christina Halmich , Markus Holzleitner
DOI:
关键词: Set (abstract data type) 、 Conservation of mass 、 Benchmark (computing) 、 Artificial intelligence 、 Constant (mathematics) 、 Inductive bias 、 Pendulum 、 Convolutional neural network 、 Conservation law 、 Computer science
摘要: Abstract The success of Convolutional Neural Networks (CNNs) in computer vision is mainly driven by their strong inductive bias, which is strong enough to allow CNNs to solve vision …
arxiv.org参考文章(87)
Tom M. Mitchell, The Need for Biases in Learning Generalizations ,(2007)
Sepp Hochreiter, Untersuchungen zu dynamischen neuronalen Netzen ,(1991)
Samy Bengio, Navdeep Jaitly, Noam Shazeer, Oriol Vinyals, Scheduled sampling for sequence prediction with recurrent Neural networks neural information processing systems. ,vol. 28, pp. 1171- 1179 ,(2015)
Keith J. Beven, Rainfall-Runoff Modelling: The Primer ,(2012)
Yoshua Bengio, Yoshua Bengio, Yoshua Bengio, Yann LeCun, Convolutional networks for images, speech, and time series The handbook of brain theory and neural networks. pp. 255- 258 ,(1998)
Sebastian Bach, Alexander Binder, Grégoire Montavon, Frederick Klauschen, Klaus-Robert Müller, Wojciech Samek, On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation. PLOS ONE. ,vol. 10, pp. 0130140- ,(2015) , 10.1371/JOURNAL.PONE.0130140
Christian Szegedy, Sergey Ioffe, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift international conference on machine learning. ,vol. 1, pp. 448- 456 ,(2015)
Michael Schmidt, Hod Lipson, Distilling Free-Form Natural Laws from Experimental Data Science. ,vol. 324, pp. 81- 85 ,(2009) , 10.1126/SCIENCE.1165893
Xin-Hua Song, Philip K. Hopke, Solving the Chemical Mass Balance Problem Using an Artificial Neural Network Environmental Science & Technology. ,vol. 30, pp. 531- 535 ,(1996) , 10.1021/ES950281O
E. Todini, Rainfall-runoff modeling — Past, present and future Journal of Hydrology. ,vol. 100, pp. 341- 352 ,(1988) , 10.1016/0022-1694(88)90191-6