English
Related papers

Related papers: NN-LUT: Neural Approximation of Non-Linear Operati…

200 papers

Transformer based models, like BERT and RoBERTa, have achieved state-of-the-art results in many Natural Language Processing tasks. However, their memory footprint, inference latency, and power consumption are prohibitive efficient inference…

Computation and Language · Computer Science 2022-05-02 Sehoon Kim , Amir Gholami , Zhewei Yao , Michael W. Mahoney , Kurt Keutzer

Transformers have revolutionized machine learning with their simple yet effective architecture. Pre-training Transformers on massive text datasets from the Internet has led to unmatched generalization for natural language understanding…

Deep neural networks, particularly those employing Rectified Linear Units (ReLU), are often perceived as complex, high-dimensional, non-linear systems. This complexity poses a significant challenge to understanding their internal learning…

Machine Learning · Computer Science 2025-11-11 Longqing Ye

While GPU clusters are the de facto choice for training large deep neural network (DNN) models today, several reasons including ease of workflow, security and cost have led to efforts investigating whether CPUs may be viable for inference…

Machine Learning · Computer Science 2024-03-13 Zhanpeng Zeng , Michael Davies , Pranav Pulijala , Karthikeyan Sankaralingam , Vikas Singh

Batch normalization (BN) is a fundamental unit in modern deep networks, in which a linear transformation module was designed for improving BN's flexibility of fitting complex data distributions. In this paper, we demonstrate properly…

Computer Vision and Pattern Recognition · Computer Science 2020-12-01 Yuhui Xu , Lingxi Xie , Cihang Xie , Jieru Mei , Siyuan Qiao , Wei Shen , Hongkai Xiong , Alan Yuille

The transformer architecture has driven many successes in a variety of tasks within the field of deep learning, in particular the recent advances in natural language processing (NLP) culminating with large language models (LLM). Adding to…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Abdullah Nazhat Abdullah , Tarkan Aydin

Transformers have become foundational architectures for both natural language and computer vision tasks. However, the high computational cost makes it quite challenging to deploy on resource-constraint devices. This paper investigates the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Jialong Guo , Xinghao Chen , Yehui Tang , Yunhe Wang

The Transformer architecture revolutionized the field of natural language processing (NLP). Transformers-based models (e.g., BERT) power many important Web services, such as search, translation, question-answering, etc. While enormous…

Computation and Language · Computer Science 2021-02-23 Dave Dice , Alex Kogan

Pre-trained large-scale language models have increasingly demonstrated high accuracy on many natural language processing (NLP) tasks. However, the limited weight storage and computational speed on hardware platforms have impeded the…

Computation and Language · Computer Science 2020-10-23 Wei Niu , Zhenglun Kong , Geng Yuan , Weiwen Jiang , Jiexiong Guan , Caiwen Ding , Pu Zhao , Sijia Liu , Bin Ren , Yanzhi Wang

Weight-only quantization has emerged as a promising solution to the deployment challenges of large language models (LLMs). However, it necessitates FP-INT operations, which make implementation on general-purpose hardware like GPUs…

Hardware Architecture · Computer Science 2025-03-11 Gunho Park , Hyeokjun Kwon , Jiwoo Kim , Jeongin Bae , Baeseong Park , Dongsoo Lee , Youngjoo Lee

Formal verification of transformers has become increasingly important due to their widespread deployment in safety-critical applications. Compared to classic neural networks, the inferences of transformers involve highly complex…

Artificial Intelligence · Computer Science 2026-05-15 Hengjie Liu , Zhenya Zhang , Jianjun Zhao

We prove that with linear transformations, both (i) two-layer self-attention and (ii) one-layer self-attention followed by a softmax function are universal approximators for continuous sequence-to-sequence functions on compact domains. Our…

Machine Learning · Computer Science 2025-12-17 Jerry Yao-Chieh Hu , Hude Liu , Hong-Yu Chen , Weimin Wu , Han Liu

Fine-tuning a pre-trained model, such as Bidirectional Encoder Representations from Transformers (BERT), has been proven to be an effective method for solving many natural language processing (NLP) tasks. However, due to the large number of…

Computation and Language · Computer Science 2024-04-01 Taha ValizadehAslani , Hualou Liang

Large-scale pre-trained language models such as BERT have contributed significantly to the development of NLP. However, those models require large computational resources, making it difficult to be applied to mobile devices where computing…

Computation and Language · Computer Science 2023-08-02 Weixin Wu , Hankz Hankui Zhuo

This paper studies the approximation property of ReLU neural networks (NNs) to piecewise constant functions with unknown interfaces in bounded regions in $\mathbb{R}^d$. Under the assumption that the discontinuity interface $\Gamma$ may be…

Functional Analysis · Mathematics 2024-10-23 Zhiqiang Cai , Junpyo Choi , Min Liu

Large Language Models (LLMs) have shown immense potential in enhancing various aspects of our daily lives, from conversational AI to search and AI assistants. However, their growing capabilities come at the cost of extremely large model…

Machine Learning · Computer Science 2025-02-27 Yingyu Liang , Jiangxuan Long , Zhenmei Shi , Zhao Song , Yufa Zhou

The ongoing decarbonisation of power systems is driving an increasing reliance on distributed energy resources, which introduces complex and nonlinear interactions that are difficult to capture in conventional optimisation models. As a…

Systems and Control · Electrical Eng. & Systems 2026-01-22 Yogesh Pipada Sunil Kumar , S. Ali Pourmousavi , Jon A. R. Liisberg , Julian Lesmos-Vinasco

Gated Linear Units (GLU) have shown great potential in enhancing neural network performance. In this paper, I introduce a novel attention mechanism called GLU Attention, which introduces nonlinearity into the values of Attention. My…

Machine Learning · Computer Science 2025-07-08 Zehao Wang

Lookup-table (LUT) based neural networks can deliver ultra-low latency and excellent hardware efficiency on FPGAs by mapping arithmetic operations directly onto the logic primitives. However, state-of-the-art LUT-aware training (LAT)…

Hardware Architecture · Computer Science 2026-04-27 Chang Sun , Zhiqiang Que , Bakhtiar Zadeh , Qibin Liu , Kevin H. Alvarez , Wayne Luk , Maria Spiropulu

We consider the use of look-up tables (LUT) to simplify the hardware implementation of a deep learning network for inferencing after weights have been successfully trained. The use of LUT replaces the matrix multiply and add operations with…

Machine Learning · Computer Science 2019-09-09 Chai Wah Wu