English
Related papers

Related papers: A Study on ReLU and Softmax in Transformer

200 papers

Recent seminal work at the intersection of deep neural networks practice and random matrix theory has linked the convergence speed and robustness of these networks with the combination of random weight initialization and nonlinear…

Machine Learning · Computer Science 2019-05-07 Pierre H. Richemond , Yike Guo

In-context reinforcement learning (ICRL) studies agents that, after pretraining, adapt to new tasks by conditioning on additional context without parameter updates. Existing theoretical analyses of ICRL largely rely on linear attention,…

Machine Learning · Computer Science 2026-05-19 Zixuan Xie , Xinyu Liu , Claire Chen , Shuze Daniel Liu , Rohan Chandra , Shangtong Zhang

Previous work has demonstrated that attention mechanisms are Turing complete. More recently, it has been shown that a looped 9-layer Transformer can function as a universal programmable computer. In contrast, the multi-layer perceptrons…

Machine Learning · Computer Science 2025-02-21 Yingyu Liang , Zhizhou Sha , Zhenmei Shi , Zhao Song , Yufa Zhou

Since its introduction, softmax attention has become the backbone of modern transformer architectures due to its expressiveness and scalability across a wide range of tasks. However, the main drawback of softmax attention is the quadratic…

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

In many information processing systems, it may be desirable to ensure that any change of the input, whether by shifting or scaling, results in a corresponding change in the system response. While deep neural networks are gradually replacing…

Computer Vision and Pattern Recognition · Computer Science 2024-02-22 Sébastien Herbreteau , Emmanuel Moebel , Charles Kervrann

Recurrent neural networks (RNNs) have long been an architecture of interest for computational models of human sentence processing. The recently introduced Transformer architecture outperforms RNNs on many natural language processing tasks…

Computation and Language · Computer Science 2022-03-31 Danny Merkx , Stefan L. Frank

Memory is critical for enabling large language model (LLM) based agents to maintain coherent behavior over long-horizon interactions. However, existing agent memory systems suffer from two key gaps: they rely on a one-size-fits-all memory…

Artificial Intelligence · Computer Science 2026-02-17 Mingfei Lu , Mengjia Wu , Feng Liu , Jiawei Xu , Weikai Li , Haoyang Wang , Zhengdong Hu , Ying Ding , Yizhou Sun , Jie Lu , Yi Zhang

When implementations of the Transformer's self-attention layer utilize SRAM instead of DRAM, they can achieve significant speedups. The Tenstorrent Grayskull architecture provides a large SRAM, distributed across a grid of cores. This work…

Machine Learning · Computer Science 2024-07-22 Moritz Thüning

Linear attention Transformers and their gated variants, celebrated for enabling parallel training and efficient recurrent inference, still fall short in recall-intensive tasks compared to traditional Transformers and demand significant…

Computation and Language · Computer Science 2024-11-01 Yu Zhang , Songlin Yang , Ruijie Zhu , Yue Zhang , Leyang Cui , Yiqiao Wang , Bolun Wang , Freda Shi , Bailin Wang , Wei Bi , Peng Zhou , Guohong Fu

Transformer has achieved great success in the NLP field by composing various advanced models like BERT and GPT. However, Transformer and its existing variants may not be optimal in capturing token distances because the position or distance…

Computation and Language · Computer Science 2021-04-13 Chuhan Wu , Fangzhao Wu , Yongfeng Huang

Transformers excel at sequence modeling but face quadratic complexity, while linear attention offers improved efficiency but often compromises recall accuracy over long contexts. In this work, we introduce Native Hybrid Attention (NHA), a…

Computation and Language · Computer Science 2026-04-16 Jusen Du , Jiaxi Hu , Tao Zhang , Weigao Sun , Yu Cheng

The transformer architecture is widely used in machine learning models and consists of two alternating sublayers: attention heads and MLPs. We prove that an MLP neuron can be implemented by a masked attention head with internal dimension 1…

Machine Learning · Computer Science 2023-09-18 Robert Huben , Valerie Morris

Softmax is popular normalization method used in machine learning. Deep learning solutions like Transformer or BERT use the softmax function intensively, so it is worthwhile to optimize its performance. This article presents our methodology…

Mathematical Software · Computer Science 2019-05-28 Jacek Czaja , Michal Gallus , Tomasz Patejko , Jian Tang

For most state-of-the-art architectures, Rectified Linear Unit (ReLU) becomes a standard component accompanied with each layer. Although ReLU can ease the network training to an extent, the character of blocking negative values may suppress…

Computer Vision and Pattern Recognition · Computer Science 2017-11-20 Xuanyi Dong , Guoliang Kang , Kun Zhan , Yi Yang

Transformer model has gained prominence as a popular deep neural network architecture for neural language processing (NLP) and computer vision (CV) applications. However, the extensive use of nonlinear operations, like softmax, poses a…

Hardware Architecture · Computer Science 2024-11-21 Shuai Dong , Junyi Yang , Xiaoqi Peng , Hongyang Shang , Ye Ke , Xiaofeng Yang , Hongjie Liu , Arindam Basu

This study delves into the effectiveness of various learning methods in improving Transformer models, focusing particularly on the Gated Residual Network Transformer (GRN-Transformer) in the context of pediatric intensive care units (PICU)…

Signal Processing · Electrical Eng. & Systems 2025-05-27 Thanh-Dung Le , Clara Macabiau , Kévin Albert , Symeon Chatzinotas , Philippe Jouvet , Rita Noumeir

Deep networks are often considered to be more expressive than shallow ones in terms of approximation. Indeed, certain functions can be approximated by deep networks provably more efficiently than by shallow ones, however, no tractable…

Machine Learning · Statistics 2021-08-27 Alberto Bietti , Francis Bach

ReLU neural-networks have been in the focus of many recent theoretical works, trying to explain their empirical success. Nonetheless, there is still a gap between current theoretical results and empirical observations, even in the case of…

Machine Learning · Computer Science 2019-06-13 Jonathan Fiat , Eran Malach , Shai Shalev-Shwartz

Element-wise activation functions play a critical role in deep neural networks via affecting the expressivity power and the learning dynamics. Learning-based activation functions have recently gained increasing attention and success. We…

Machine Learning · Computer Science 2020-10-05 Dengsheng Chen , Jun Li , Kai Xu

Despite their prevalence in neural networks we still lack a thorough theoretical characterization of ReLU layers. This paper aims to further our understanding of ReLU layers by studying how the activation function ReLU interacts with the…

Machine Learning · Computer Science 2019-08-13 Sören Dittmer , Emily J. King , Peter Maass
‹ Prev 1 4 5 6 7 8 10 Next ›