Sequence Prediction Using Neural Network Classiers

Yanpeng Zhao, Shanbo Chu, Yang Zhou, Kewei Tu
Proceedings of The 13th International Conference on Grammatical Inference, PMLR 57:164-169, 2017.

Abstract

Being able to guess the next element of a sequence is an important question in many fields. In this paper we present our approaches used in the Sequence Prediction ChallengE (SPiCe), whose goal is to compare the different approaches to that problem on the same datasets. We model sequence prediction as a classification problem and adapt three different neural network models to tackle it. The experimental results show that our neural network based approaches produce better overall performance than the baseline approaches provided in the competition. In the actual competition, we won the second place using these approaches.

Cite this Paper

BibTeX
@InProceedings{pmlr-v57-zhao16, title = {Sequence Prediction Using Neural Network Classiers}, author = {Zhao, Yanpeng and Chu, Shanbo and Zhou, Yang and Tu, Kewei}, booktitle = {Proceedings of The 13th International Conference on Grammatical Inference}, pages = {164--169}, year = {2017}, editor = {Verwer, Sicco and Zaanen, Menno van and Smetsers, Rick}, volume = {57}, series = {Proceedings of Machine Learning Research}, address = {Delft, The Netherlands}, month = {05--07 Oct}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v57/zhao16.pdf}, url = {http://proceedings.mlr.press/v57/zhao16.html}, abstract = {Being able to guess the next element of a sequence is an important question in many fields. In this paper we present our approaches used in the Sequence Prediction ChallengE (SPiCe), whose goal is to compare the different approaches to that problem on the same datasets. We model sequence prediction as a classification problem and adapt three different neural network models to tackle it. The experimental results show that our neural network based approaches produce better overall performance than the baseline approaches provided in the competition. In the actual competition, we won the second place using these approaches.} }
Endnote
%0 Conference Paper %T Sequence Prediction Using Neural Network Classiers %A Yanpeng Zhao %A Shanbo Chu %A Yang Zhou %A Kewei Tu %B Proceedings of The 13th International Conference on Grammatical Inference %C Proceedings of Machine Learning Research %D 2017 %E Sicco Verwer %E Menno van Zaanen %E Rick Smetsers %F pmlr-v57-zhao16 %I PMLR %P 164--169 %U http://proceedings.mlr.press/v57/zhao16.html %V 57 %X Being able to guess the next element of a sequence is an important question in many fields. In this paper we present our approaches used in the Sequence Prediction ChallengE (SPiCe), whose goal is to compare the different approaches to that problem on the same datasets. We model sequence prediction as a classification problem and adapt three different neural network models to tackle it. The experimental results show that our neural network based approaches produce better overall performance than the baseline approaches provided in the competition. In the actual competition, we won the second place using these approaches.
RIS
TY - CPAPER TI - Sequence Prediction Using Neural Network Classiers AU - Yanpeng Zhao AU - Shanbo Chu AU - Yang Zhou AU - Kewei Tu BT - Proceedings of The 13th International Conference on Grammatical Inference DA - 2017/01/16 ED - Sicco Verwer ED - Menno van Zaanen ED - Rick Smetsers ID - pmlr-v57-zhao16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 57 SP - 164 EP - 169 L1 - http://proceedings.mlr.press/v57/zhao16.pdf UR - http://proceedings.mlr.press/v57/zhao16.html AB - Being able to guess the next element of a sequence is an important question in many fields. In this paper we present our approaches used in the Sequence Prediction ChallengE (SPiCe), whose goal is to compare the different approaches to that problem on the same datasets. We model sequence prediction as a classification problem and adapt three different neural network models to tackle it. The experimental results show that our neural network based approaches produce better overall performance than the baseline approaches provided in the competition. In the actual competition, we won the second place using these approaches. ER -
APA
Zhao, Y., Chu, S., Zhou, Y. & Tu, K.. (2017). Sequence Prediction Using Neural Network Classiers. Proceedings of The 13th International Conference on Grammatical Inference, in Proceedings of Machine Learning Research 57:164-169 Available from http://proceedings.mlr.press/v57/zhao16.html.

Related Material