Goto

Collaborating Authors

Can recurrent neural networks warp time?

arXiv.org Machine Learning

Successful recurrent models such as long short-term memories (LSTMs) and gated recurrent units (GRUs) use ad hoc gating mechanisms. Empirically these models have been found to improve the learning of medium to long term temporal dependencies and to help with vanishing gradient issues. We prove that learnable gates in a recurrent model formally provide quasi- invariance to general time transformations in the input data. We recover part of the LSTM architecture from a simple axiomatic approach. This result leads to a new way of initializing gate biases in LSTMs and GRUs. Ex- perimentally, this new chrono initialization is shown to greatly improve learning of long term dependencies, with minimal implementation effort.


AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks

arXiv.org Machine Learning

Recurrent neural networks have gained widespread use in modeling sequential data. Learning long-term dependencies using these models remains difficult though, due to exploding or vanishing gradients. In this paper, we draw connections between recurrent networks and ordinary differential equations. A special form of recurrent networks called the AntisymmetricRNN is proposed under this theoretical framework, which is able to capture long-term dependencies thanks to the stability property of its underlying differential equation. Existing approaches to improving RNN trainability often incur significant computation overhead. In comparison, AntisymmetricRNN achieves the same goal by design. AntisymmetricRNN exhibits much more predictable dynamics. It outperforms regular LSTM models on tasks requiring long-term memory and matches the performance on tasks where short-term dependencies dominate despite being much simpler. Modeling complex temporal dependencies in sequential data using RNNs, especially the long-term dependencies, remains an open challenge.


Regularizing Recurrent Networks - On Injected Noise and Norm-based Methods

arXiv.org Machine Learning

Advancements in parallel processing have lead to a surge in multilayer perceptrons' (MLP) applications and deep learning in the past decades. Recurrent Neural Networks (RNNs) give additional representational power to feedforward MLPs by providing a way to treat sequential data. However, RNNs are hard to train using conventional error backpropagation methods because of the difficulty in relating inputs over many time-steps. Regularization approaches from MLP sphere, like dropout and noisy weight training, have been insufficiently applied and tested on simple RNNs. Moreover, solutions have been proposed to improve convergence in RNNs but not enough to improve the long term dependency remembering capabilities thereof. In this study, we aim to empirically evaluate the remembering and generalization ability of RNNs on polyphonic musical datasets. The models are trained with injected noise, random dropout, norm-based regularizers and their respective performances compared to well-initialized plain RNNs and advanced regularization methods like fast-dropout. We conclude with evidence that training with noise does not improve performance as conjectured by a few works in RNN optimization before ours.


Dilated Recurrent Neural Networks

Neural Information Processing Systems

Learning with recurrent neural networks (RNNs) on long sequences is a notoriously difficult task. There are three major challenges: 1) complex dependencies, 2) vanishing and exploding gradients, and 3) efficient parallelization. In this paper, we introduce a simple yet effective RNN connection structure, the DilatedRNN, which simultaneously tackles all of these challenges. The proposed architecture is characterized by multi-resolution dilated recurrent skip connections and can be combined flexibly with diverse RNN cells. Moreover, the DilatedRNN reduces the number of parameters needed and enhances training efficiency significantly, while matching state-of-the-art performance (even with standard RNN cells) in tasks involving very long-term dependencies. To provide a theory-based quantification of the architecture's advantages, we introduce a memory capacity measure, the mean recurrent length, which is more suitable for RNNs with long skip connections than existing measures. We rigorously prove the advantages of the DilatedRNN over other recurrent neural architectures. The code for our method is publicly available at https://github.com/code-terminator/DilatedRNN.


Dilated Recurrent Neural Networks

Neural Information Processing Systems

Learning with recurrent neural networks (RNNs) on long sequences is a notoriously difficult task. There are three major challenges: 1) complex dependencies, 2) vanishing and exploding gradients, and 3) efficient parallelization. In this paper, we introduce a simple yet effective RNN connection structure, the DilatedRNN, which simultaneously tackles all of these challenges. The proposed architecture is characterized by multi-resolution dilated recurrent skip connections and can be combined flexibly with diverse RNN cells. Moreover, the DilatedRNN reduces the number of parameters needed and enhances training efficiency significantly, while matching state-of-the-art performance (even with standard RNN cells) in tasks involving very long-term dependencies.