Content deleted Content added
Citation bot (talk | contribs) m Add: year, author pars. 1-5. | You can use this bot yourself. Report bugs here. | Activated by User:AManWithNoPlan | All pages linked from User:AManWithNoPlan/sandbox2 | via #UCB_webform_linked |
Citation bot (talk | contribs) Add: arxiv, bibcode. | You can use this bot yourself. Report bugs here. | Activated by Zppix | Category:Artificial neural networks | via #UCB_Category |
||
Line 1:
{{Orphan|date=March 2016}}
'''Bidirectional [[Recurrent neural networks|Recurrent Neural Networks]]''' ('''BRNN''') connect two hidden layers of opposite directions to the same output. With this form of [[Generative model|generative deep learning]], the output layer can get information from past (backwards) and future (forward) states simultaneously. Invented in 1997 by Schuster and Paliwal,<ref name="Schuster">Schuster, Mike, and Kuldip K. Paliwal. "[https://www.researchgate.net/profile/Mike_Schuster/publication/3316656_Bidirectional_recurrent_neural_networks/links/56861d4008ae19758395f85c.pdf Bidirectional recurrent neural networks]." Signal Processing, IEEE Transactions on 45.11 (1997): 2673-2681.2. Awni Hannun, Carl Case, Jared Casper, Bryan Catanzaro, Greg Diamos, Erich Elsen, Ryan</ref> BRNNs were introduced to increase the amount of input information available to the network. For example, [[multilayer perceptron]] (MLPs) and [[time delay neural network]] (TDNNs) have limitations on the input data flexibility, as they require their input data to be fixed. Standard [[recurrent neural network]] (RNNs) also have restrictions as the future input information cannot be reached from the current state. On the contrary, BRNNs do not require their input data to be fixed. Moreover, their future input information is reachable from the current state. <ref>{{Cite document|title=Recent Advances in Recurrent Neural Networks|arxiv = 1801.01078|last1 = Salehinejad|first1 = Hojjat|last2 = Sankar|first2 = Sharan|last3 = Barfett|first3 = Joseph|last4 = Colak|first4 = Errol|last5 = Valaee|first5 = Shahrokh|year = 2017|bibcode = 2018arXiv180101078S}}</ref>
BRNN are especially useful when the context of the input is needed. For example, in handwriting recognition, the performance can be enhanced by knowledge of the letters located before and after the current letter.
Line 25:
*Protein Structure Prediction<ref>Baldi, Pierre, et al. "[https://academic.oup.com/bioinformatics/article-pdf/15/11/937/693153/150937.pdf Exploiting the past and the future in protein secondary structure prediction]." Bioinformatics 15.11 (1999): 937-946.</ref><ref>Pollastri, Gianluca, and Aoife Mclysaght. "[https://academic.oup.com/bioinformatics/article/21/8/1719/250163 Porter: a new, accurate server for protein secondary structure prediction]." Bioinformatics 21.8 (2005): 1719-1720.</ref>
*Part-of-speech tagging
*Dependency Parsing<ref>{{Cite journal|last=Kiperwasser|first=Eliyahu|last2=Goldberg|first2=Yoav|date=2016|title=Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations|url=https://www.aclweb.org/anthology/Q16-1023/|journal=Transactions of the Association for Computational Linguistics|language=en-us|volume=4|pages=313–327|doi=10.1162/tacl_a_00101|arxiv=1603.04351|bibcode=2016arXiv160304351K}}</ref>
*Entity Extraction<ref>{{Cite arxiv|last=Dernoncourt|first=Franck|last2=Lee|first2=Ji Young|last3=Szolovits|first3=Peter|date=2017-05-15|title=NeuroNER: an easy-to-use program for named-entity recognition based on neural networks|eprint=1705.05487|class=cs.CL}}</ref>
| |||