paper-with-me

홈 › Papers

Input-Output Equivalence of Unitary and Contractive RNNs

2019-12-01 · NeurIPS 2019 12 · Melikasadat Emami, Mojtaba Sahraee Ardakan, Sundeep Rangan, Alyson K. Fletcher

Unitary recurrent neural networks (URNNs) have been proposed as a method to overcome the vanishing and exploding gradient problem in modeling data with long-term dependencies. A basic question is how restrictive is the unitary constraint on the possible input-output mappings of such a network? This works shows that for any contractive RNN with ReLU activations, there is a URNN with at most twice the number of hidden states and the identical input-output mapping. Hence, with ReLU activations, URNNs are as expressive as general RNNs. In contrast, for certain smooth activations, it is shown that the input-output mapping of an RNN cannot be matched with a URNN, even with an arbitrary number of states. The theoretical results are supported by experiments on modeling of slowly-varying dynamical systems.

📄 PDF Abstract BibTeX

Code (1)

melikaemami/URNN 공식 구현 tf

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Input-Output Equivalence of Unitary and Contractive RNNs

2019-10-30 · M. Emami, M. Sahraee-Ardakan, S. Rangan, A. K. Fletcher

Unitary recurrent neural networks (URNNs) have been proposed as a method to overcome the vanishing and exploding gradient problem in modeling data with long-term dependencies. A basic question is how restrictive is the u…

Full-Capacity Unitary Recurrent Neural Networks

2016-10-31 · NeurIPS 2016 12 · Scott Wisdom, Thomas Powers, John R. Hershey, Jonathan Le Roux 외

Recurrent neural networks are powerful models for processing sequential data, but they are generally plagued by vanishing and exploding gradient problems. Unitary recurrent neural networks (uRNNs), which use unitary recu…

Open-Ended Question AnsweringSequential Image Classification

Complex Evolution Recurrent Neural Networks (ceRNNs)

2019-06-05 · Izhak Shafran, Tom Bagby, R. J. Skerry-Ryan

Unitary Evolution Recurrent Neural Networks (uRNNs) have three attractive properties: (a) the unitary property, (b) the complex-valued nature, and (c) their efficient linear operators. The literature so far does not addr…

speech-recognitionSpeech Recognition

Gated Orthogonal Recurrent Units: On Learning to Forget

2017-06-08 · Li Jing, Caglar Gulcehre, John Peurifoy, Yichen Shen 외

We present a novel recurrent neural network (RNN) based model that combines the remembering ability of unitary RNNs with the ability of gated RNNs to effectively forget redundant/irrelevant information in its memory. We …

DenoisingQuestion Answering

Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs

2016-12-15 · ICML 2017 8 · Li Jing, Yichen Shen, Tena Dubček, John Peurifoy 외

Using unitary (instead of general) matrices in artificial neural networks (ANNs) is a promising way to solve the gradient explosion/vanishing problem, as well as to enable ANNs to learn long-term correlations in the data…

Permuted-MNIST