Filters








4 Hits in 0.64 sec

MuFuRU: The Multi-Function Recurrent Unit [article]

Dirk Weissenborn, Tim Rocktäschel
2016 arXiv   pre-print
We propose Multi-Function Recurrent Units (MuFuRUs) that allow for arbitrary differentiable functions as composition operations.  ...  Recurrent neural networks such as the GRU and LSTM found wide adoption in natural language processing and achieve state-of-the-art results for many tasks.  ...  Acknowledgments This research was partially supported by Microsoft Research through its PhD Scholarship Programme and by the German Federal Ministry of Education and Research (BMBF) through the projects  ... 
arXiv:1606.03002v1 fatcat:njf5zg4rmnbyle2w565wkz4b5u

Multiple-Weight Recurrent Neural Networks

Zhu Cao, Linlin Wang, Gerard de Melo
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
However, current architectures are not particularly adept at dealing with tasks involving multi-faceted contents.  ...  We present a framework for adapting RNN-based models and analyze the properties of this approach.  ...  In contrast, the recent Multi-Function Recurrent Units (Mu-FuRUs) adopt an elaborate gating mechanism that allows for additional differentiable functions as composition operations [Weissenborn and Rocktäschel  ... 
doi:10.24963/ijcai.2017/205 dblp:conf/ijcai/CaoWM17 fatcat:5tjcojf7rzahpmiebh45mrjrwy

Autoregressive Convolutional Neural Networks for Asynchronous Time Series [article]

Mikołaj Bińkowski, Gautier Marti, Philippe Donnat
2018 arXiv   pre-print
The model is inspired by standard autoregressive (AR) models and gating mechanisms used in recurrent neural networks.  ...  It involves an AR-like weighting system, where the final predictor is obtained as a weighted sum of adjusted regressors, while the weights are datadependent functions learnt through a convolutional network  ...  ACKNOWLEDGEMENTS Authors would like to thank Hellebore Capital Ltd. for providing data for the experiments.  ... 
arXiv:1703.04122v4 fatcat:aqiz75ukm5drxkqspiyq3fhf2a

Lishe Lishe ii EDITORS REVIEWERS

Joyceline Kaganda, Ms Mselle, Ms Mella, Ms Sigalla, Joyce Kinabo, John Msuya, Theobard Mosha
2013 LISHE Tanzania Food and Nutrition Journal   unpublished
The reducing sugars in the extracted material of the regular, fermented, malted and malted/fermented flours from both food grade white Macia and the red tannin sorghum samples were determined by the (DNS  ...  The amounts of soluble proteins in the supernatant material were measured using the Lowry method (Lowry et al, 1951).  ...  offered during the entire period the review.  ... 
fatcat:kafzs6yu4zg2zmkunl34bmrgzy