English
Related papers

Related papers: Gated recurrent neural networks discover attention

200 papers

Deep learning has recently demonstrated state-of-the art performance on key tasks related to the maintenance of computer systems, such as intrusion detection, denial of service attack detection, hardware and software system failures, and…

Machine Learning · Computer Science 2018-03-15 Andy Brown , Aaron Tuor , Brian Hutchinson , Nicole Nichols

This paper analyzes the behavior of stack-augmented recurrent neural network (RNN) models. Due to the architectural similarity between stack RNNs and pushdown transducers, we train stack RNN models on a number of tasks, including string…

Neural and Evolutionary Computing · Computer Science 2018-09-11 Yiding Hao , William Merrill , Dana Angluin , Robert Frank , Noah Amsel , Andrew Benz , Simon Mendelsohn

Neural network-based approaches have become the driven forces for Natural Language Processing (NLP) tasks. Conventionally, there are two mainstream neural architectures for NLP tasks: the recurrent neural network (RNN) and the convolution…

Computation and Language · Computer Science 2020-08-13 Zhenyu Liu , Chaohong Lu , Haiwei Huang , Shengfei Lyu , Zhenchao Tao

In this work, we analyze the capabilities and practical limitations of neural networks (NNs) for sequence-based signal processing which can be seen as an omnipresent property in almost any modern communication systems. In particular, we…

Information Theory · Computer Science 2019-11-22 Daniel Tandler , Sebastian Dörner , Sebastian Cammerer , Stephan ten Brink

We introduce MinimalRNN, a new recurrent neural network architecture that achieves comparable performance as the popular gated RNNs with a simplified structure. It employs minimal updates within RNN, which not only leads to efficient…

Machine Learning · Statistics 2018-06-21 Minmin Chen

Transformers are highly parallel but are limited to computations in the TC$^0$ complexity class, excluding tasks such as entity tracking and code execution that provably require greater expressive power. Motivated by this limitation, we…

Machine Learning · Computer Science 2026-05-15 Mayank Mishra , Shawn Tan , Ion Stoica , Joseph Gonzalez , Tri Dao

Gating is a key feature in modern neural networks including LSTMs, GRUs and sparsely-gated deep neural networks. The backbone of such gated networks is a mixture-of-experts layer, where several experts make regression decisions and gating…

Machine Learning · Computer Science 2020-06-19 Ashok Vardhan Makkuva , Sewoong Oh , Sreeram Kannan , Pramod Viswanath

Understanding the internal dynamics of Recurrent Neural Networks (RNNs) is crucial for advancing their interpretability and improving their design. This study introduces an innovative information-theoretic method to identify and analyze…

Machine Learning · Computer Science 2025-10-03 Arend Hintze , Asadullah Najam , Jory Schossau

Attention networks have proven to be an effective approach for embedding categorical inference within a deep neural network. However, for many tasks we may want to model richer structural dependencies without abandoning end-to-end training.…

Computation and Language · Computer Science 2017-02-17 Yoon Kim , Carl Denton , Luong Hoang , Alexander M. Rush

The shift from Convolutional Neural Networks to Transformers has reshaped computer vision, yet these two architectural families are typically viewed as fundamentally distinct. We argue that convolution and self-attention, despite their…

Computer Vision and Pattern Recognition · Computer Science 2025-11-24 Mingi Kang , Jeová Farias Sales Rocha Neto

Understanding the asymptotic behavior of gradient-descent training of deep neural networks is essential for revealing inductive biases and improving network performance. We derive the infinite-time training limit of a mathematically…

Machine Learning · Statistics 2022-02-08 Samuel Lippl , L. F. Abbott , SueYeon Chung

We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or…

Machine Learning · Statistics 2018-02-06 Petar Veličković , Guillem Cucurull , Arantxa Casanova , Adriana Romero , Pietro Liò , Yoshua Bengio

Several recent works demonstrate that transformers can implement algorithms like gradient descent. By a careful construction of weights, these works show that multiple layers of transformers are expressive enough to simulate iterations of…

Machine Learning · Computer Science 2023-11-13 Kwangjun Ahn , Xiang Cheng , Hadi Daneshmand , Suvrit Sra

While self-attention mechanism has shown promising results for many vision tasks, it only considers the current features at a time. We show that such a manner cannot take full advantage of the attention mechanism. In this paper, we present…

Computer Vision and Pattern Recognition · Computer Science 2020-07-13 Xu Ma , Jingda Guo , Sihai Tang , Zhinan Qiao , Qi Chen , Qing Yang , Song Fu

Graph neural networks (GNNs) have been widely adopted in engineering applications such as social network analysis, chemical research and computer vision. However, their efficacy is severely compromised by the inherent homophily assumption,…

Machine Learning · Computer Science 2026-04-13 Yi Luo , Xu Sun , Guangchun Luo , Aiguo Chen

Convolutional-deconvolution networks can be adopted to perform end-to-end saliency detection. But, they do not work well with objects of multiple scales. To overcome such a limitation, in this work, we propose a recurrent attentional…

Computer Vision and Pattern Recognition · Computer Science 2016-04-13 Jason Kuen , Zhenhua Wang , Gang Wang

Recently recurrent neural networks (RNN) has been very successful in handling sequence data. However, understanding RNN and finding the best practices for RNN is a difficult task, partly because there are many competing and complex hidden…

Neural and Evolutionary Computing · Computer Science 2016-04-01 Guo-Bing Zhou , Jianxin Wu , Chen-Lin Zhang , Zhi-Hua Zhou

In this paper, we propose a novel approach that enhances recurrent neural networks (RNNs) by incorporating path signatures into their gating mechanisms. Our method modifies both Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU)…

Machine Learning · Computer Science 2025-02-14 Rémi Genet , Hugo Inzirillo

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…

Machine Learning · Statistics 2019-02-27 Bo Chang , Minmin Chen , Eldad Haber , Ed H. Chi

Several variants of recurrent neural networks (RNNs) with orthogonal or unitary recurrent matrices have recently been developed to mitigate the vanishing/exploding gradient problem and to model long-term dependencies of sequences. However,…

Machine Learning · Computer Science 2019-11-20 Kyle Helfrich , Qiang Ye