J Grid Computing https://doi.org/10.1007/s10723-018-9444-4 Residual Recurrent Highway Networks for Learning Deep Sequence Prediction Models Tehseen Zia · Saad Razzaq Received: 20 February 2018 / Accepted: 28 May 2018 © Springer Science+Business Media B.V., part of Springer Nature 2018 Abstract A contemporary approach for acquiring experiments with Penn TreeBank, the model achieved the computational gains of depth in recurrent neu- 60.3 perplexity and outperformed baseline and related ral networks (RNNs) is to hierarchically stack mul- models that we tested. tiple recurrent layers. However, such performance gains come with the cost of challenging optimiza- Keywords Deep learning · Recurrent neural tion of hierarchal RNNs (HRNNs) which are deep networks · Sequence modeling · Highway networks · both hierarchically and temporally. The researchers Residual learning have exclusively highlighted the significance of using shortcuts for learning deep hierarchical representa- tions and deep temporal dependencies. However, no 1 Introduction significant efforts are made to unify these finding into a single framework for learning deep HRNNs. We Recurrent neural networks (RNNs) are specifically designed for processing data in sequential steps. This propose residual recurrent highway network (R2HN) that contains highways within temporal structure of allows the network to seize sequential associations between data instances. The
Journal of Grid Computing – Springer Journals
Published: Jun 6, 2018
It’s your single place to instantly
discover and read the research
that matters to you.
Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.
All for just $49/month
Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly
Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.
Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.
Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.
All the latest content is available, no embargo periods.
“Hi guys, I cannot tell you how much I love this resource. Incredible. I really believe you've hit the nail on the head with this site in regards to solving the research-purchase issue.”Daniel C.
“Whoa! It’s like Spotify but for academic articles.”@Phil_Robichaud
“I must say, @deepdyve is a fabulous solution to the independent researcher's problem of #access to #information.”@deepthiw
“My last article couldn't be possible without the platform @deepdyve that makes journal papers cheaper.”@JoseServera