International Conference on Learning Representations · 2014 · 582 citations · 39 references
ComputingComputer ScienceMachine LearningNatural Language ProcessingNeural CircuitryDeep LearningLanguage ModelingNeural NetworksSpeech RecognitionFeedforward Neural NetworksNeural Language ModelsOperatorsRecurrent Neural Network Language ModelsRecurrent Neural Networks
Abstract: In this paper, we explore different ways to extend a recurrent neural network (RNN) to a \textit{deep} RNN. We start by arguing that the concept of depth in an RNN is not as clear as it is in feedforward neural networks. By carefully analyzing and understanding the architecture of an RNN, however, we find three points of an RNN which may be made deeper; (1) input-to-hidden function, (2) hidden-to-hidden transition and (3) hidden-to-output function. Based on this observation, we propose two novel architectures of a deep RNN which are orthogonal to an earlier attempt of stacking multiple recurrent layers to build a deep RNN (Schmidhuber, 1992; El Hihi and Bengio, 1996). We provide an alternative interpretation of these deep RNNs using a novel framework based on neural operators. The proposed deep RNNs are empirically evaluated on the tasks of polyphonic music prediction and language modeling. The experimental result supports our claim that the proposed deep RNNs benefit from the depth and outperform the conventional, shallow RNNs.
39
Learning representations by back-propagating errors
David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams · Nature · 1986 · 30.9K citations
Distributed Representations of Words and Phrases and their Compositionality
Tomáš Mikolov, Ilya Sutskever, Kai Chen et al. · arXiv (Cornell University) · 2013 · 18.1K citations · Full text
Multilayer feedforward networks are universal approximators
HornikK., StinchcombeM., WhiteH. · Neural Networks · 1989 · 9.4K citations