paper-with-me

Papers

Kronecker Recurrent Units

2017-05-29 · ICML 2018 7 · Cijo Jose, Moustpaha Cisse, Francois Fleuret

Our work addresses two important issues with recurrent neural networks: (1) they are over-parameterized, and (2) the recurrence matrix is ill-conditioned. The former increases the sample complexity of learning and the training time. The latter causes the vanishing and exploding gradient problem. We present a flexible recurrent neural network model called Kronecker Recurrent Units (KRU). KRU achieves parameter efficiency in RNNs through a Kronecker factored recurrent matrix. It overcomes the ill-conditioning of the recurrent matrix by enforcing soft unitary constraints on the factors. Thanks to the small dimensionality of the factors, maintaining these constraints is computationally efficient. Our experimental results on seven standard data-sets reveal that KRU can reduce the number of parameters by three orders of magnitude in the recurrent weight matrix compared to the existing recurrent models, without trading the statistical performance. These results in particular show that while there are advantages in having a high dimensional recurrent space, the capacity of the recurrent part of the model can be dramatically reduced.

📄 PDF Abstract BibTeX arXiv:1705.10142

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Approximating Real-Time Recurrent Learning with Random Kronecker Factors

2018-05-28 · NeurIPS 2018 12 · Asier Mujika, Florian Meier, Angelika Steger

Despite all the impressive advances of recurrent neural networks, sequential data is still in need of better modelling. Truncated backpropagation through time (TBPTT), the learning algorithm most widely used in practice,…

Memorization

Optimal Kronecker-Sum Approximation of Real Time Recurrent Learning

2019-02-11 · Frederik Benzing, Marcelo Matheus Gauy, Asier Mujika, Anders Martinsson 외

One of the central goals of Recurrent Neural Networks (RNNs) is to learn long-term dependencies in sequential data. Nevertheless, the most popular training method, Truncated Backpropagation through Time (TBPTT), categori…

Memorization

Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

2014-12-11 · Junyoung Chung, Caglar Gulcehre, Kyunghyun Cho, Yoshua Bengio

In this paper we compare different types of recurrent units in recurrent neural networks (RNNs). Especially, we focus on more sophisticated units that implement a gating mechanism, such as a long short-term memory (LSTM)…

Music Modeling

Kronecker CP Decomposition with Fast Multiplication for Compressing RNNs

2020-08-21 · Dingheng Wang, Bijiao Wu, Guangshe Zhao, Man Yao 외

Recurrent neural networks (RNNs) are powerful in the tasks oriented to sequential data, such as natural language processing and video recognition. However, since the modern RNNs, including long-short term memory (LSTM) a…

Tensor DecompositionVideo Recognition

On Similarity

2021-11-02 · Luciano da F. Costa

The objective quantification of similarity between two mathematical structures constitutes a recurrent issue in science and technology. In the present work, we developed a principled approach that took the Kronecker's de…