English
Related papers

Related papers: A Survey of Retentive Network

200 papers

The training of deep residual neural networks (ResNets) with backpropagation has a memory cost that increases linearly with respect to the depth of the network. A way to circumvent this issue is to use reversible architectures. In this…

Machine Learning · Computer Science 2021-07-23 Michael E. Sander , Pierre Ablin , Mathieu Blondel , Gabriel Peyré

Due to the highly parallelizable architecture, Transformer is faster to train than RNN-based models and popularly used in machine translation tasks. However, at inference time, each output word requires all the hidden states of the…

Computation and Language · Computer Science 2019-09-06 Chengyi Wang , Shuangzhi Wu , Shujie Liu

Catastrophic forgetting and capacity saturation are the central challenges of any parametric lifelong learning system. In this work, we study these challenges in the context of sequential supervised learning with an emphasis on recurrent…

Machine Learning · Computer Science 2019-09-10 Shagun Sodhani , Sarath Chandar , Yoshua Bengio

Recently, end-to-end sequence-to-sequence models for speech recognition have gained significant interest in the research community. While previous architecture choices revolve around time-delay neural networks (TDNN) and long short-term…

Computation and Language · Computer Science 2019-05-06 Ngoc-Quan Pham , Thai-Son Nguyen , Jan Niehues , Markus Müller , Sebastian Stüker , Alexander Waibel

Memory retention challenges in deep neural architectures have ongoing limitations in the ability to process and recall extended contextual information. Token dependencies degrade as sequence length increases, leading to a decline in…

Computation and Language · Computer Science 2025-03-26 Frederick Dillon , Gregor Halvorsen , Simon Tattershall , Magnus Rowntree , Gareth Vanderpool

Real-time recurrent learning (RTRL) for sequence-processing recurrent neural networks (RNNs) offers certain conceptual advantages over backpropagation through time (BPTT). RTRL requires neither caching past activations nor truncating…

Machine Learning · Computer Science 2024-02-29 Kazuki Irie , Anand Gopalakrishnan , Jürgen Schmidhuber

It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies the channel-wise attention on different network branches to…

Computer Vision and Pattern Recognition · Computer Science 2021-01-01 Hang Zhang , Chongruo Wu , Zhongyue Zhang , Yi Zhu , Haibin Lin , Zhi Zhang , Yue Sun , Tong He , Jonas Mueller , R. Manmatha , Mu Li , Alexander Smola

Reinforcement learning (RL) agents performing complex tasks must be able to remember observations and actions across sizable time intervals. This is especially true during the initial learning stages, when exploratory behaviour can increase…

Machine Learning · Computer Science 2018-05-15 Thomas Stepleton , Razvan Pascanu , Will Dabney , Siddhant M. Jayakumar , Hubert Soyer , Remi Munos

The key to a Transformer model is the self-attention mechanism, which allows the model to analyze an entire sequence in a computationally efficient manner. Recent work has suggested the possibility that general attention mechanisms used by…

Machine Learning · Computer Science 2020-01-01 Thomas Dowdell , Hongyu Zhang

While hardware-software co-design has significantly improved the efficiency of neural network inference, modeling the training phase remains a critical yet underexplored challenge. Training workloads impose distinct constraints,…

Machine Learning · Computer Science 2026-03-17 Jérémy Morlier , Robin Geens , Stef Cuyckens , Arne Symons , Marian Verhelst , Vincent Gripon , Mathieu Léonardon

Neural networks have been successfully applied in applications with a large amount of labeled data. However, the task of rapid generalization on new concepts with small training data while preserving performances on previously learned ones…

Machine Learning · Computer Science 2017-06-09 Tsendsuren Munkhdalai , Hong Yu

The trend towards increasingly deep neural networks has been driven by a general observation that increasing depth increases the performance of a network. Recently, however, evidence has been amassing that simply increasing depth may not be…

Computer Vision and Pattern Recognition · Computer Science 2016-12-01 Zifeng Wu , Chunhua Shen , Anton van den Hengel

This paper presents the design of an associative memory with feedback that is capable of on-line temporal sequence learning. A framework for on-line sequence learning has been proposed, and different sequence learning models have been…

Neural and Evolutionary Computing · Computer Science 2007-05-23 J. Bose , S. B. Furber , J. L. Shapiro

Heterogeneous network data with rich nodal information become increasingly prevalent across multidisciplinary research, yet accurately modeling complex nodal heterogeneity and simultaneously selecting influential nodal attributes remains an…

Methodology · Statistics 2026-04-14 Zhaoyu Xing , Xiufan Yu

The Receptance Weighted Key Value (RWKV) model offers a novel alternative to the Transformer architecture, merging the benefits of recurrent and attention-based systems. Unlike conventional Transformers, which depend heavily on…

Computation and Language · Computer Science 2025-01-07 Zhiyuan Li , Tingyu Xia , Yi Chang , Yuan Wu

The success of deep neural networks (DNN) in machine perception applications such as image classification and speech recognition comes at the cost of high computation and storage complexity. Inference of uncompressed large scale DNN models…

Machine Learning · Computer Science 2020-07-06 Yihao Fang , Shervin Manzuri Shalmani , Rong Zheng

Transformer-based language models utilize the attention mechanism for substantial performance improvements in almost all natural language processing (NLP) tasks. Similar attention structures are also extensively studied in several other…

Computation and Language · Computer Science 2023-05-17 Nurullah Sevim , Ege Ozan Özyedek , Furkan Şahinuç , Aykut Koç

We consider the problem of selective prediction (also known as reject option) in deep neural networks, and introduce SelectiveNet, a deep neural architecture with an integrated reject option. Existing rejection mechanisms are based mostly…

Machine Learning · Computer Science 2019-06-28 Yonatan Geifman , Ran El-Yaniv

Learning-based methods have demonstrated remarkable performance in solving inverse problems, particularly in image reconstruction tasks. Despite their success, these approaches often lack theoretical guarantees, which are crucial in…

Numerical Analysis · Mathematics 2025-10-21 Clemens Arndt , Judith Nickel

Deep Neural networks are efficient and flexible models that perform well for a variety of tasks such as image, speech recognition and natural language understanding. In particular, convolutional neural networks (CNN) generate a keen…

Machine Learning · Computer Science 2018-12-20 Yesmina Jaafra , Jean Luc Laurent , Aline Deruyver , Mohamed Saber Naceur