English
Related papers

Related papers: Universal Transformers

200 papers

Transformer-based neural network architectures achieve state-of-the-art results in different domains, from natural language processing (NLP) to computer vision (CV). The key idea of Transformers, the attention mechanism, has already led to…

Machine Learning · Computer Science 2023-11-07 Alina Ermilova , Nikita Baramiia , Valerii Kornilov , Sergey Petrakov , Alexey Zaytsev

Recurrent neural networks (RNNs) are capable of learning features and long term dependencies from sequential and time-series data. The RNNs have a stack of non-linear units where at least one connection between units forms a directed cycle.…

Neural and Evolutionary Computing · Computer Science 2018-02-26 Hojjat Salehinejad , Sharan Sankar , Joseph Barfett , Errol Colak , Shahrokh Valaee

Language models with recurrent depth, also referred to as universal or looped when considering transformers, are defined by the capacity to increase their computation through the repetition of layers. Recent efforts in pretraining have…

Machine Learning · Computer Science 2025-10-17 Jonas Geiping , Xinyu Yang , Guinan Su

As a surrogate for computationally intensive meso-scale simulation of woven composites, this article presents Recurrent Neural Network (RNN) models. Leveraging the power of transfer learning, the initialization challenges and sparse data…

Materials Science · Physics 2024-07-08 Ehsan Ghane , Martin Fagerström , Mohsen Mirkhalaf

This review aims to conduct a comparative analysis of liquid neural networks (LNNs) and traditional recurrent neural networks (RNNs) and their variants, such as long short-term memory networks (LSTMs) and gated recurrent units (GRUs). The…

Machine Learning · Computer Science 2025-10-10 Shilong Zong , Alex Bierly , Almuatazbellah Boker , Hoda Eldardiry

We propose a new model for unsupervised document embedding. Leading existing approaches either require complex inference or use recurrent neural networks (RNN) that are difficult to parallelize. We take a different route and develop a…

Computation and Language · Computer Science 2018-02-21 Chundi Liu , Shunan Zhao , Maksims Volkovs

Recently, a new recurrent neural network (RNN) named the Legendre Memory Unit (LMU) was proposed and shown to achieve state-of-the-art performance on several benchmark datasets. Here we leverage the linear time-invariant (LTI) memory…

Machine Learning · Computer Science 2021-05-12 Narsimha Chilkuri , Chris Eliasmith

Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or "temporally deep", are effective for tasks involving sequences, visual and otherwise.…

Computer Vision and Pattern Recognition · Computer Science 2016-06-02 Jeff Donahue , Lisa Anne Hendricks , Marcus Rohrbach , Subhashini Venugopalan , Sergio Guadarrama , Kate Saenko , Trevor Darrell

Medical image segmentation have drawn massive attention as it is important in biomedical image analysis. Good segmentation results can assist doctors with their judgement and further improve patients' experience. Among many available…

Image and Video Processing · Electrical Eng. & Systems 2021-09-20 Youyang Sha , Yonghong Zhang , Xuquan Ji , Lei Hu

Recently, neural machine translation (NMT) has been extended to multilinguality, that is to handle more than one translation direction with a single system. Multilingual NMT showed competitive performance against pure bilingual systems.…

Computation and Language · Computer Science 2018-06-22 Surafel M. Lakew , Mauro Cettolo , Marcello Federico

Though early successes of Statistical Machine Translation (SMT) systems are attributed in part to the explicit modelling of the interaction between any two source and target units, e.g., alignment, the recent Neural Machine Translation…

Computation and Language · Computer Science 2020-02-19 Yanyang Li , Qiang Wang , Tong Xiao , Tongran Liu , Jingbo Zhu

We explore options to use Transformer networks in neural transducer for end-to-end speech recognition. Transformer networks use self-attention for sequence modeling and comes with advantages in parallel computation and capturing contexts.…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-30 Ching-Feng Yeh , Jay Mahadeokar , Kaustubh Kalgaonkar , Yongqiang Wang , Duc Le , Mahaveer Jain , Kjell Schubert , Christian Fuegen , Michael L. Seltzer

This paper describes a language representation model which combines the Bidirectional Encoder Representations from Transformers (BERT) learning mechanism described in Devlin et al. (2018) with a generalization of the Universal Transformer…

Computation and Language · Computer Science 2019-05-17 Alon Rozental , Zohar Kelrich , Daniel Fleischer

Transfer learning from a high-resource language pair `parent' has been proven to be an effective way to improve neural machine translation quality for low-resource language pairs `children.' However, previous approaches build a custom…

Computation and Language · Computer Science 2019-09-23 Mozhdeh Gheini , Jonathan May

In Transformer-based neural machine translation (NMT), the positional encoding mechanism helps the self-attention networks to learn the source representation with order dependency, which makes the Transformer-based NMT achieve…

Computation and Language · Computer Science 2020-04-09 Kehai Chen , Rui Wang , Masao Utiyama , Eiichiro Sumita

This work establishes a rigorous theoretical foundation for analyzing deep learning systems by leveraging Infinite Time Turing Machines (ITTMs), which extend classical computation into transfinite ordinal steps. Using ITTMs, we reinterpret…

Computational Complexity · Computer Science 2025-06-09 Rukmal Weerawarana , Maxwell Braun

Recurrent Neural Networks (RNNs) are general-purpose parallel-sequential computers. The program of an RNN is its weight matrix. How to learn useful representations of RNN weights that facilitate RNN analysis as well as downstream tasks?…

Machine Learning · Computer Science 2025-04-30 Vincent Herrmann , Francesco Faccio , Jürgen Schmidhuber

Convolutional neural networks (CNN) based tracking approaches have shown favorable performance in recent benchmarks. Nonetheless, the chosen CNN features are always pre-trained in different task and individual components in tracking systems…

Computer Vision and Pattern Recognition · Computer Science 2017-11-21 Zheng Zhu , Guan Huang , Wei Zou , Dalong Du , Chang Huang

As NNs permeate various scientific and industrial domains, understanding the universality and reusability of their representations becomes crucial. At their core, these networks create intermediate neural representations, indicated as…

Machine Learning · Computer Science 2024-06-18 Luca Moschella

Reduction of training time is an important issue in many tasks like patent translation involving neural networks. Data parallelism and model parallelism are two common approaches for reducing training time using multiple graphics processing…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-09-10 Junya Ono , Masao Utiyama , Eiichiro Sumita