TY - GEN
T1 - Multiple-weight recurrent neural networks
AU - Cao, Zhu
AU - Wang, Linlin
AU - De Melo, Gerard
PY - 2017
Y1 - 2017
N2 - Recurrent neural networks (RNNs) have enjoyed great success in speech recognition, natural language processing, etc. Many variants of RNNs have been proposed, including vanilla RNNs, LSTMs, and GRUs. However, current architectures are not particularly adept at dealing with tasks involving multi-faceted contents, i.e., data with a bimodal or multimodal distribution. In this work, we solve this problem by proposing Multiple-Weight RNNs and LSTMs, which rely on multiple weight matrices to better mimic the human ability of switching between contexts. We present a framework for adapting RNN-based models and analyze the properties of this approach. Our detailed experimental results show that our model outperforms previous work across a range of different tasks and datasets.
AB - Recurrent neural networks (RNNs) have enjoyed great success in speech recognition, natural language processing, etc. Many variants of RNNs have been proposed, including vanilla RNNs, LSTMs, and GRUs. However, current architectures are not particularly adept at dealing with tasks involving multi-faceted contents, i.e., data with a bimodal or multimodal distribution. In this work, we solve this problem by proposing Multiple-Weight RNNs and LSTMs, which rely on multiple weight matrices to better mimic the human ability of switching between contexts. We present a framework for adapting RNN-based models and analyze the properties of this approach. Our detailed experimental results show that our model outperforms previous work across a range of different tasks and datasets.
UR - http://www.scopus.com/inward/record.url?scp=85031908568&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85031908568&partnerID=8YFLogxK
U2 - 10.24963/ijcai.2017/205
DO - 10.24963/ijcai.2017/205
M3 - Conference contribution
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 1483
EP - 1489
BT - 26th International Joint Conference on Artificial Intelligence, IJCAI 2017
A2 - Sierra, Carles
PB - International Joint Conferences on Artificial Intelligence
T2 - 26th International Joint Conference on Artificial Intelligence, IJCAI 2017
Y2 - 19 August 2017 through 25 August 2017
ER -