paper-with-me

홈 › Papers

Complex Unitary Recurrent Neural Networks using Scaled Cayley Transform

2018-11-09 · Kehelwala D. G. Maduranga, Kyle E. Helfrich, Qiang Ye

Recurrent neural networks (RNNs) have been successfully used on a wide range of sequential data problems. A well known difficulty in using RNNs is the \textit{vanishing or exploding gradient} problem. Recently, there have been several different RNN architectures that try to mitigate this issue by maintaining an orthogonal or unitary recurrent weight matrix. One such architecture is the scaled Cayley orthogonal recurrent neural network (scoRNN) which parameterizes the orthogonal recurrent weight matrix through a scaled Cayley transform. This parametrization contains a diagonal scaling matrix consisting of positive or negative one entries that can not be optimized by gradient descent. Thus the scaling matrix is fixed before training and a hyperparameter is introduced to tune the matrix for each particular task. In this paper, we develop a unitary RNN architecture based on a complex scaled Cayley transform. Unlike the real orthogonal case, the transformation uses a diagonal scaling matrix consisting of entries on the complex unit circle which can be optimized using gradient descent and no longer requires the tuning of a hyperparameter. We also provide an analysis of a potential issue of the modReLU activiation function which is used in our work and several other unitary RNNs. In the experiments conducted, the scaled Cayley unitary recurrent neural network (scuRNN) achieves comparable or better results than scoRNN and other unitary RNNs without fixing the scaling matrix.

📄 PDF Abstract BibTeX arXiv:1811.04142

Code (1)

Gayan225/scuRNN 공식 구현 tf

Methods 이 논문이 사용한 방법론

modReLU modReLU is an activation that is a modification of a ReLU. It is a pointwise nonlinearity, $\sigma\_{modReLU}\left(z\right) : C…
Unitary RNN A Unitary RNN is a recurrent neural network architecture that uses a unitary hidden to hidden matrix. Specifically they concern dynamics of the form: $$ h\_{t} =…

Similar Papers 제목 키워드 기반

Orthogonal Recurrent Neural Networks with Scaled Cayley Transform

2017-07-29 · ICML 2018 7 · Kyle Helfrich, Devin Willmott, Qiang Ye

Recurrent Neural Networks (RNNs) are designed to handle sequential data but suffer from vanishing or exploding gradients. Recent work on Unitary Recurrent Neural Networks (uRNNs) have been used to address this issue and …

Orthogonal Gated Recurrent Unit with Neumann-Cayley Transformation

2022-08-12 · Edison Mucllari, Vasily Zadorozhnyy, Cole Pospisil, Duc Nguyen 외

In recent years, using orthogonal matrices has been shown to be a promising approach in improving Recurrent Neural Networks (RNNs) with training, stability, and convergence, particularly, to control gradients. While Gate…

Complex-Valued Unitary Representations as Classification Heads for Improved Uncertainty Quantification in Deep Neural Networks

2026-02-17 · Akbar Anbar Jafari, Cagri Ozcinar, Gholamreza Anbarjafari arxiv

Modern deep neural networks achieve high predictive accuracy but remain poorly calibrated: their confidence scores do not reliably reflect the true probability of correctness. We propose a quantum-inspired classification…

Out-of-Distribution DetectionSentiment Analysis

Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform

2020-02-04 · ICLR 2020 1 · Jun Li, Li Fuxin, Sinisa Todorovic

Strictly enforcing orthonormality constraints on parameter matrices has been shown advantageous in deep learning. This amounts to Riemannian optimization on the Stiefel manifold, which, however, is computationally expens…

Riemannian optimization

Quantum-enhanced Large Language Models on Quantum Hardware via Cayley Unitary Adapters

2026-05-07 · Borja Aizpurua, Sukhbinder Singh, Augustine Kshetrimayum, Saeed S. Jahromi 외 arxiv

Large language models (LLMs) have transformed artificial intelligence, yet classical architectures impose a fundamental constraint: every trainable parameter demands classical memory that scales unfavourably with model s…