English
Related papers

Related papers: A Study on ReLU and Softmax in Transformer

200 papers

Attention mechanisms, particularly softmax attention, have been instrumental in the success of transformer-based models such as GPT. However, the quadratic memory complexity of softmax attention with respect to sequence length poses…

Machine Learning · Computer Science 2026-02-20 Gabriel Mongaras , Trevor Dohm , Eric C. Larson

Softmax attention is the principle backbone of foundation models for various artificial intelligence applications, yet its quadratic complexity in sequence length can limit its inference throughput in long-context settings. To address this…

Machine Learning · Computer Science 2024-12-10 Jerome Sieber , Carmen Amo Alonso , Alexandre Didier , Melanie N. Zeilinger , Antonio Orvieto

Biological neural systems employ diverse neurotransmitters -- glutamate, GABA, dopamine, acetylcholine -- to implement distinct signal-processing modalities within shared neural circuits. In contrast, modern transformers apply a single…

Machine Learning · Computer Science 2026-03-17 Daniel Nobrega Medeiros

The Transformer architecture, a cornerstone of modern Large Language Models (LLMs), has achieved extraordinary success in sequence modeling, primarily due to its attention mechanism. However, despite its power, the standard attention…

Machine Learning · Computer Science 2026-01-08 Zichuan Fu , Wentao Song , Guojing Li , Yejing Wang , Xian Wu , Yimin Deng , Hanyu Yan , Yefeng Zheng , Xiangyu Zhao

We demonstrate a magnetic tunnel junction injected with spin Hall current to exhibit linear rotation of magnetization of the free-ferromagnet using only the spin current. Using the linear resistance change of the MTJ, we devise a circuit…

Mesoscale and Nanoscale Physics · Physics 2023-07-26 Venkatesh Vadde , Bhaskaran Muralidharan , Abhishek Sharma

Transformers have been established as the most popular backbones in sequence modeling, mainly due to their effectiveness in in-context retrieval tasks and the ability to learn at scale. Their quadratic memory and time complexity, however,…

Computation and Language · Computer Science 2025-05-30 Ali Behrouz , Zeman Li , Praneeth Kacham , Majid Daliri , Yuan Deng , Peilin Zhong , Meisam Razaviyayn , Vahab Mirrokni

There has been a rapid advance of custom hardware (HW) for accelerating the inference speed of deep neural networks (DNNs). Previously, the softmax layer was not a main concern of DNN accelerating HW, because its portion is relatively small…

Machine Learning · Computer Science 2021-11-23 Ihor Vasyltsov , Wooseok Chang

Current Transformer-based natural language understanding (NLU) models heavily rely on dataset biases, while failing to handle real-world out-of-distribution (OOD) instances. Many methods have been proposed to deal with this issue, but they…

Computation and Language · Computer Science 2023-06-06 Xiaoyue Wang , Lijie Wang , Xin Liu , Suhang Wu , Jinsong Su , Hua Wu

Transformer is the backbone of modern NLP models. In this paper, we propose RealFormer, a simple and generic technique to create Residual Attention Layer Transformer networks that significantly outperform the canonical Transformer and its…

Machine Learning · Computer Science 2021-09-14 Ruining He , Anirudh Ravula , Bhargav Kanagal , Joshua Ainslie

Speech recognition is largely taking advantage of deep learning, showing that substantial benefits can be obtained by modern Recurrent Neural Networks (RNNs). The most popular RNNs are Long Short-Term Memory (LSTMs), which typically reach…

Computation and Language · Computer Science 2017-10-03 Mirco Ravanelli , Philemon Brakel , Maurizio Omologo , Yoshua Bengio

Transformers achieve state-of-the-art performance for natural language processing tasks by pre-training on large-scale text corpora. They are extremely compute-intensive and have very high sample complexity. Memory replay is a mechanism…

Machine Learning · Computer Science 2022-05-23 Rui Liu , Barzan Mozafari

The architecture of Transformer is based entirely on self-attention, and has been shown to outperform models that employ recurrence on sequence transduction tasks such as machine translation. The superior performance of Transformer has been…

Machine Learning · Computer Science 2019-08-29 Vikas K. Garg , Inderjit S. Dhillon , Hsiang-Fu Yu

Motivated by the growing theoretical understanding of neural networks that employ the Rectified Linear Unit (ReLU) as their activation function, we revisit the use of ReLU activation functions for learning implicit neural representations…

Image and Video Processing · Electrical Eng. & Systems 2024-08-05 Joseph Shenouda , Yamin Zhou , Robert D. Nowak

Common recurrent neural architectures scale poorly due to the intrinsic difficulty in parallelizing their state computations. In this work, we propose the Simple Recurrent Unit (SRU), a light recurrent unit that balances model capacity and…

Computation and Language · Computer Science 2018-09-10 Tao Lei , Yu Zhang , Sida I. Wang , Hui Dai , Yoav Artzi

Understanding how Transformer-based language models store and retrieve factual associations is critical for improving interpretability and enabling targeted model editing. Prior work, primarily on GPT-style models, has identified MLP…

Computation and Language · Computer Science 2025-09-11 Minyeong Choe , Haehyun Cho , Changho Seo , Hyunil Kim

With the increasing demand for practical applications of Large Language Models (LLMs), many attention-efficient models have been developed to balance performance and computational cost. However, the adversarial robustness of these models…

Computation and Language · Computer Science 2024-09-17 Xiaojing Fan , Chunliang Tao

Transformers have shown remarkable performance in both natural language processing (NLP) and computer vision (CV) tasks. However, their real-time inference speed and efficiency are limited due to the inefficiency in Softmax and Layer…

Machine Learning · Computer Science 2025-10-21 Wenxun Wang , Shuchang Zhou , Wenyu Sun , Peiqin Sun , Yongpan Liu

State-of-the-art results on neural machine translation often use attentional sequence-to-sequence models with some form of convolution or recursion. Vaswani et al. (2017) propose a new architecture that avoids recurrence and convolution…

Artificial Intelligence · Computer Science 2017-11-08 Karim Ahmed , Nitish Shirish Keskar , Richard Socher

The Transformer is an extremely powerful and prominent deep learning architecture. In this work, we challenge the commonly held belief in deep learning that going deeper is better, and show an alternative design approach that is building…

Machine Learning · Computer Science 2022-11-10 Jason Ross Brown , Yiren Zhao , Ilia Shumailov , Robert D Mullins

Reinforcement learning (RL) has seen significant advancements through the application of various neural network architectures. In this study, we systematically investigate the performance of several neural networks in RL tasks, including…

Machine Learning · Computer Science 2025-05-22 Ivan Smirnov , Shangding Gu