English
Related papers

Related papers: ParaRNN: Unlocking Parallel Training of Nonlinear …

200 papers

The design of recurrent neural networks (RNNs) to accurately process sequential inputs with long-time dependencies is very challenging on account of the exploding and vanishing gradient problem. To overcome this, we propose a novel RNN…

Machine Learning · Computer Science 2021-08-19 T. Konstantin Rusch , Siddhartha Mishra

Recurrent neural networks are increasing popular models for sequential learning. Unfortunately, although the most effective RNN architectures are perhaps excessively complicated, extensive searches have not found simpler alternatives. This…

Machine Learning · Computer Science 2016-05-26 David Balduzzi , Muhammad Ghifary

Recurrent Neural Network (RNN) is a fundamental structure in deep learning. Recently, some works study the training process of over-parameterized neural networks, and show that over-parameterized networks can learn functions in some notable…

Machine Learning · Computer Science 2022-01-27 Lifu Wang , Bo Shen , Bo Hu , Xing Cao

The predictive learning of spatiotemporal sequences aims to generate future images by learning from the historical context, where the visual dynamics are believed to have modular structures that can be learned with compositional subsystems.…

Machine Learning · Computer Science 2022-04-12 Yunbo Wang , Haixu Wu , Jianjin Zhang , Zhifeng Gao , Jianmin Wang , Philip S. Yu , Mingsheng Long

Recurrent neural networks (RNNs) are known to be difficult to train due to the gradient vanishing and exploding problems and thus difficult to learn long-term patterns and construct deep networks. To address these problems, this paper…

Computer Vision and Pattern Recognition · Computer Science 2020-12-10 Shuai Li , Wanqing Li , Chris Cook , Yanbo Gao

Sequence modeling is a critical yet challenging task with wide-ranging applications, especially in time series forecasting for domains like weather prediction, temperature monitoring, and energy load forecasting. Transformers, with their…

Machine Learning · Computer Science 2025-04-15 Qisai Liu , Zhanhong Jiang , Joshua R. Waite , Chao Liu , Aditya Balu , Soumik Sarkar

Binary Balanced Tree RvNNs (BBT-RvNNs) enforce sequence composition according to a preset balanced binary tree structure. Thus, their non-linear recursion depth is just $\log_2 n$ ($n$ being the sequence length). Such logarithmic scaling…

Machine Learning · Computer Science 2023-11-09 Jishnu Ray Chowdhury , Cornelia Caragea

This paper develops alternative hyperparameters for specifying sparse Recurrent Neural Networks (RNNs). These hyperparameters allow for varying sparsity within the trainable weight matrices of the model while improving overall performance.…

Machine Learning · Computer Science 2025-09-19 Quincy Hershey , Randy Paffenroth

Typical methods for supervised sequence modeling are built upon the recurrent neural networks to capture temporal dependencies. One potential limitation of these methods is that they only model explicitly information interactions between…

Computer Vision and Pattern Recognition · Computer Science 2019-08-27 Canmiao Fu , Wenjie Pei , Qiong Cao , Chaopeng Zhang , Yong Zhao , Xiaoyong Shen , Yu-Wing Tai

The definition of a Neural Network architecture is one of the most critical and challenging tasks to perform. In this paper, we propose ParallelMLPs. ParallelMLPs is a procedure to enable the training of several independent Multilayer…

Machine Learning · Computer Science 2022-06-20 Felipe Costa Farias , Teresa Bernarda Ludermir , Carmelo Jose Albanez Bastos-Filho

Recently, recurrent neural networks (RNNs) as powerful sequence models have re-emerged as a potential acoustic model for statistical parametric speech synthesis (SPSS). The long short-term memory (LSTM) architecture is particularly…

Computation and Language · Computer Science 2016-01-12 Zhizheng Wu , Simon King

The growing demand for real-time DNN applications on edge devices necessitates faster inference of increasingly complex models. Although many devices include specialized accelerators (e.g., mobile GPUs), dynamic control-flow operators and…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-15 Chong Tang , Hao Dai , Jagmohan Chauhan

Deep Neural Network (DNN) frameworks use distributed training to enable faster time to convergence and alleviate memory capacity limitations when training large models and/or using high dimension inputs. With the steady increase in datasets…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-04-20 Albert Njoroge Kahira , Truong Thao Nguyen , Leonardo Bautista Gomez , Ryousei Takano , Rosa M Badia , Mohamed Wahib

Recurrent neural networks (RNNs) have shown excellent performance in processing sequence data. However, they are both complex and memory intensive due to their recursive nature. These limitations make RNNs difficult to embed on mobile…

Machine Learning · Computer Science 2019-01-28 Arash Ardakani , Zhengyun Ji , Sean C. Smithson , Brett H. Meyer , Warren J. Gross

The key challenge of sequence representation learning is to capture the long-range temporal dependencies. Typical methods for supervised sequence representation learning are built upon recurrent neural networks to capture temporal…

Computer Vision and Pattern Recognition · Computer Science 2022-07-21 Wenjie Pei , Xin Feng , Canmiao Fu , Qiong Cao , Guangming Lu , Yu-Wing Tai

Neural networks are increasingly evolving towards training large models with big data, a method that has demonstrated superior performance across many tasks. However, this approach introduces an urgent problem: current deep learning models…

Machine Learning · Computer Science 2024-12-02 Wei Wang , Qing Li

Recently, machine learning methods have provided a broad spectrum of original and efficient algorithms based on Deep Neural Networks (DNN) to automatically predict an outcome with respect to a sequence of inputs. Recurrent hidden cells…

Machine Learning · Computer Science 2017-02-15 Mohamed Bouaziz , Mohamed Morchid , Richard Dufour , Georges Linarès , Renato De Mori

Linear recurrent neural networks (RNNs) and state-space models (SSMs) such as Mamba have become promising alternatives to softmax-attention as sequence mixing layers in Transformer architectures. Current models, however, do not exhibit the…

Machine Learning · Computer Science 2025-10-27 Sajad Movahedi , Felix Sarnthein , Nicola Muca Cirone , Antonio Orvieto

Recurrent neural networks (RNN) are used in many real-world text and speech applications. They include complex modules such as recurrence, exponential-based activation, gate interaction, unfoldable normalization, bi-directional dependence,…

Machine Learning · Computer Science 2022-02-16 Eyyüb Sari , Vanessa Courville , Vahid Partovi Nia

Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention. Although widely adopted, transformers require scaling memory and compute linearly during inference. A recent stream of work…